NVIDIA AI Inference Infrastructure as a Service
Hyper Talent Solutions delivers NVIDIA AI Inference Infrastructure as a Service, optimised for running trained AI models at scale. The service provides low-latency, high-throughput GPU inference platforms with secure operations, supporting real-time and batch AI use cases for public sector services.
Features
- GPU-optimised platforms for AI inference workloads.
- Low-latency inference execution capabilities.
- High-throughput processing for large workloads.
- Secure isolation of inference services.
- Scalable inference capacity on demand.
- Monitoring of inference performance metrics.
- Access control enforcement for inference platforms.
- Lifecycle management of inference environments.
- High availability inference service design.
- Operational reporting for inference usage.
Benefits
- Faster AI inference responses.
- Faster AI inference responses. Improved responsiveness of digital services.
- Scalable consumption of AI inference.
- Secure execution of AI models.
- Predictable inference performance.
- Reduced infrastructure management complexity.
- Enhanced citizen-facing service performance.
- Lower latency for real-time use cases.
- Reliable and resilient inference platforms.
- Enterprise-grade AI service delivery.
Pricing
- Education pricing available
Service documents
Request an accessible format
Framework
G-Cloud 15
Service ID
6 3 1 6 1 7 3 2 1 6 1 2 9 1 5
Contact
HYPER TALENT SOLUTIONS LTD
Amri Nazeer
Telephone: 07772866727
Email: hts.operations@hypertalentsolutions.com
About your service
- Service categories
-
Systems Infrastructure Software
System and service management
- IT operations management
- IT service management
IT automation and configuration management
- Workload management
- Datacentre system and application control
- Multi cloud support
- Yes
Service scope
- Software add-on or extension
- Yes, but can also be used as a standalone service
- What software services is the service an extension to
- The service can extend existing NVIDIA GPU platforms, NVIDIA AI Enterprise, and GPU-enabled private cloud or on-premises environments. It also integrates with container platforms, AI development frameworks, data analytics platforms, and virtualisation or orchestration services that run on NVIDIA-accelerated infrastructure, enabling organisations to enhance existing AI and high-performance computing capabilities.
- Cloud deployment model
-
- Public cloud
- Private cloud
- Community cloud
- Hybrid cloud
- Service constraints
- N/A
- System requirements
-
- A standard browser, either desktop or mobile
- Connection to the internet
User support
- Email or online ticketing support
- Yes
- Support response times
- Every VMware service includes support as standard.
- User can manage status and priority of support tickets
- Yes
- Online ticketing support accessibility
- WCAG 2.2 AAA
- Phone support
- Yes
- Phone support availability
- 9 to 5 (UK time), Monday to Friday
- Web chat support
- No
- Onsite support
- Yes
- Support levels
- HTS typical Incident & Service Management requests are as follows: 1. Priority One: Response time in 30 mins, resolution in under 2 hours 2. Priority Two: Response time in 30 mins, resolution in <8 hours 3. Priority three: Response time in 30 mins, resolution in <48 hours Service levels start with items being raised in the Aurentiq Service Desk. Priority 1 and Priority 2 items are in relation to Service Hours. Priority 2 and 3 are in relation to Core Service Hours. Aurentiq will provide an SLA to meet the above metrics to 95%.
- Support available to third parties
- Yes
Onboarding and offboarding
- Getting started
- We help users start using the service through a structured onboarding and enablement approach designed for public-sector environments. Each engagement begins with an onboarding session to confirm service scope, user roles, security requirements and access controls. We provision user accounts, apply role-based permissions, and configure initial service settings to ensure users can safely access the platform from day one. Users are provided with comprehensive online documentation, including service guides, API references, operational runbooks and usage instructions. These materials explain how to request services, monitor usage, interpret dashboards and follow governance processes. Documentation is regularly updated to reflect platform changes and service improvements. We provide remote training sessions covering platform navigation, self-service provisioning, monitoring and operational best practices. Training can be tailored for different audiences, such as administrators, application teams and service consumers. Where required, we can also deliver onsite workshops for larger teams or complex deployments, subject to agreement. Ongoing support is available through scheduled knowledge-transfer sessions, service clinics and access to technical specialists. This approach ensures users quickly gain confidence using the service while maintaining security, compliance and operational consistency.
- Service documentation
- Yes
- Documentation formats
-
- HTML
- Other
- Other documentation formats
- Kindle
- End-of-contract data extraction
- At the end of the contract, users can extract their data using standard, supported NVIDIA and platform-native export mechanisms. AI models, datasets, configurations and logs can be exported via secure APIs, container registries, object storage exports, or industry-standard formats agreed during onboarding. Where required, data can be transferred to customer-designated environments or storage locations under controlled security processes. Aurentiq supports an agreed exit and handover process, including validation of exported data. Once data extraction is confirmed, all remaining customer data is securely deleted from the service in line with contractual, security and regulatory requirements.
- End-of-contract process
- At the end of the contract, HTS supports a controlled service exit. Users retain access for the agreed notice period to extract their data, after which access is revoked and all remaining customer data is securely deleted in accordance with contractual, security and regulatory requirements. The contract price includes access to the NVIDIA Lot 2a service, standard onboarding, platform operations, monitoring, lifecycle management, security controls and support. Additional costs may apply for optional services such as bespoke integrations, extended data migration support, specialist consulting, onsite training, or exit assistance beyond the standard handover process.
- Documentation accessibility standard
- WCAG 2.2 AAA
Using the service
- Web browser interface
- Yes
- Supported browsers
-
- Microsoft Edge
- Firefox
- Chrome
- Safari
- Opera
- Application to install
- No
- Designed for use on mobile devices
- Yes
- Differences between the mobile and desktop service
- N/A
- Service interface
- No
- User support accessibility
- WCAG 2.2 AAA
- API
- Yes
- What users can and can't do using the API
- Users can use the service APIs to securely provision and manage NVIDIA-accelerated AI infrastructure and platform services. Through authenticated API calls, users can request GPU compute resources, deploy and manage AI workloads, configure inference services, monitor performance metrics, and integrate the service with automation, MLOps or service management tools. APIs support lifecycle actions such as starting, stopping, scaling workloads, and retrieving usage, health and audit information. Users can make configuration changes within their allocated resources, such as adjusting workload parameters, scaling capacity within approved limits, and updating application-level settings. Role-based access controls ensure only authorised actions are permitted. Users cannot use the APIs to access or modify the underlying physical infrastructure, GPU firmware, host operating systems, or managed platform components. Platform-wide configuration, patching, upgrades, security hardening and multi-tenant isolation are not exposed. Users cannot exceed assigned quotas, bypass governance controls, or access other tenants’ data or workloads.
- API documentation
- Yes
- API documentation formats
-
- Open API (also known as Swagger)
- HTML
- ODF
- API sandbox or test environment
- No
- Customisation available
- No
Scaling
- Independence of resources
- We guarantee independence of resources through logical isolation, policy-based controls and capacity management built into the service. Each user or tenant is allocated defined compute, storage and network resources with enforced quotas and limits, preventing one tenant’s demand from impacting others. Workloads are isolated using secure multi-tenant architectures and software-defined controls. Continuous monitoring tracks utilisation and performance across tenants, and automated controls prevent resource contention. Capacity is proactively managed to maintain headroom, and service-level thresholds trigger scaling or corrective actions, ensuring consistent performance and availability for all users.
Analytics
- Service usage metrics
- Yes
- Metrics types
-
CPU
Disk
HTTP request and response status
Memory
Network
Number of active instances - Reporting types
-
- API access
- Real-time dashboards
- Reports on request
- Resource tagging
- Yes
- FOCUS resource tagging
- Yes
Resellers
- Supplier type
- Reseller providing extra support
- Organisation whose services are being resold
- NVIDIA
Staff security
- Staff security clearance
- Conforms to BS7858:2019
- Government security clearance
- Developed Vetting (DV)
Asset protection
- Knowledge of data storage and processing locations
- Yes
- Data storage and processing locations
-
- United Kingdom
- European Economic Area (EEA)
- Other locations
- User control over data storage and processing locations
- Yes
- Datacentre security standards
- Complies with a recognised standard (for example CSA CCM version 4.0)
- Penetration testing frequency
- Less than once a year
- Penetration testing approach
- Another external penetration testing organisation
- Protecting data at rest
-
- Physical access control, complying with SSAE-18 / ISAE 3402
- Physical access control, complying with another standard
- Encryption of all physical media
- Data sanitisation process
- Yes
- Equipment disposal approach
- Complying with a recognised standard, for example CSA CCM v4.0, CAS (Sanitisation) or ISO/IEC 27001
- Data sanitisation type
-
- Deleted data can’t be directly accessed / Cryptographic Erasure
- Explicit overwriting of storage before reallocation / Secure Erase
- Physical Destruction / Hardware containing data is completely destroyed
Data importing and exporting
- Data export approach
- Users export their data using standard, supported NVIDIA and platform-native export mechanisms. Data such as AI models, datasets, configurations and logs can be exported through secure APIs, container image registries, object storage exports or industry-standard formats. Exports can be transferred to customer-designated environments under agreed security controls. All export activities are authenticated, authorised and logged to meet security, audit and compliance requirements.
- Data export formats
-
- CSV
- ODF
- Data import formats
-
- CSV
- ODF
Data-in-transit protection
- Data protection between buyer and supplier networks
-
- Private network or public sector network
- TLS (version 1.2 or above)
- IPsec or TLS VPN gateway
- Legacy SSL and TLS (under version 1.2)
- Data protection within supplier network
- TLS (version 1.2 or above)
Availability and resilience
- Guaranteed availability
- We guarantee 99.95% availability and can include this within any SLA on request.
- Approach to resilience
- Available on request.
- Outage reporting
- There is an API available and email/SMS alerts too.
Identity and authentication
- User authentication needed
- Yes
- User authentication
-
- Multi-Factor Authentication (MFA)
- Public key authentication (including by TLS client certificate)
- Identity federation with existing provider (for example Google Apps)
- Dedicated link (for example VPN)
- Access restrictions in management interfaces and support channels
-
Management access for service support and delivery is done through multiple layers of controls including, but not limited to, multiple 2 factor authentication, bastion host and proxy control and segregation of duties. These controls are in scope for SSAE-18 auditing and evidences through the SOC 2/ISAE3402 report.
Access to the management interface for the customer to configure their salesforce environment, is configured by the customer themselves. The options are outlined in the above response. Robust application design and testing ensures that users without administrative access rights cannot access more sensitive areas of the application. - Access restriction testing frequency
- At least once a year
- Management access authentication
-
- Multi-Factor Authentication (MFA)
- Public key authentication (including by TLS client certificate)
- Identity federation with existing provider (for example Google Apps)
- Dedicated link (for example VPN)
Audit information for users
- Access to user activity audit information
- Users have access to real-time audit information
- How long user audit data is stored for
- User-defined
- Access to supplier activity audit information
- Users have access to real-time audit information
- How long supplier audit data is stored for
- User-defined
- How long system logs are stored for
- User-defined
Security governance
- Named board-level person responsible for service security
- Yes
- Security governance certified
- Yes
- Security governance standards
-
- ISO/IEC 27001
- Other
- Other security governance standards
-
Cyber Essentials
GDPR - Information security policies and processes
- Adherence to Cyber Essentials guidelines
- Software Security Code of Practice
- Yes
Operational security
- Configuration and change management standard
- Supplier-defined controls
- Configuration and change management approach
- We use DevOps and DevSecOps process using GitLab as our version control and Pen testing through development
- Vulnerability management type
- Supplier-defined controls
- Vulnerability management approach
- We receive updates and risk alerts from our supplier security centres or use pen testing with custom software and respond to deploy patches within 48 hours or sooner if require.
- Protective monitoring type
- Supplier-defined controls
- Protective monitoring approach
- We receive updates and risk alerts from our supplier security centres or use pen testing with custom software and respond to deploy patches within 48 hours or sooner if require
- Incident management type
- Supplier-defined controls
- Incident management approach
- We receive updates and risk alerts from our supplier security centres or use pen testing with custom software and respond to deploy patches within 48 hours or sooner if require. Incidents are then recorded, reviewed and integrated into future risk assessment and mitigation processes.
- Post-quantum cryptography secure
- Yes
Secure development
- Approach to secure software development best practice
- Supplier-defined process
Public sector networks
- Connection to public sector networks
- Yes
- Connected networks
-
- Public Services Network (PSN)
- Police National Network (PNN)
Pricing
- Discount for educational organisations
- Yes
- Free trial available
- No
Discount percentage by annual call-off contract value (excluding VAT)
- Less than £250,000
- 0%
- Between £250,000 and £500,000
- 0.25%
- Between £500,001 and £1,000,000
- 0.35%
- Between £1,000,001 and £2,500,000
- 0.45%
- Between £2,500,001 and £5,000,000
- 0.5%
- Over £5,000,001
- 0.6%
Non-mandatory Standards and certifications
- ISO/IEC 27001 certification
- Yes
- Who accredited the ISO/IEC 27001
- LMS
- ISO/IEC 27001 accreditation date
- Friday 14 February 2025
- What the ISO/IEC 27001 doesn’t cover
- N/A
- ISO 28000:2022 certification
- No
- ISO 9001 certification
- Yes
- Who accredited the ISO 9001 certification
- LMS
- ISO 9001 accreditation date
- Saturday 12 April 2025
- What the ISO 9001 doesn’t cover
- N/A
- Quality management systems (QMS)
- Yes
- CSA STAR certification
- No
- PCI certification
- No
- Cyber essentials
- Yes
- Please provide your Cyber Essentials Certificate Number
- A5571775-cb03-4ecb-927c-3cdcfd7a84fa
- Cyber essentials plus
- No
- Cyber Essentials Alternative
- In relation to the services you do not have a current and valid Cyber Essentials Plus certificate which has been awarded by one of the government approved Cyber Essentials accreditation bodies but you are working towards gaining it, and will be in a position to confirm that you have been awarded a current and valid Cyber Essentials Plus certificate by one of the government approved accreditation bodies within 12 months of the date of award.
- Other security certifications
- No
Social value
- Section B - Commitment for Future: Delivery
-
-
Mission: Kick start economic growth. To secure the highest sustained growth in the G7 - with good jobs and productivity growth in every part of the country making everyone, not just a few, better off.
Policy Outcome 1: Fair work: That offers fair wages and good working conditions. Help people get a job, stay in work, and progress in their careers, with good employment opportunities across the country. Notes: Where there is a large proportion of labour costs in the contract, commercial teams should consider MAC in Outcome 1 as a priority
- New or retained jobs on the contract workforce in the relevant area that meet the criteria set out in MAC 1b, 1c and 1d
- New apprenticeships on the contract workforce in the relevant area that meet the criteria set out in MAC 1b
- Providing opportunities for, and measuring and monitoring of, staff workforce conditions over time, including employee engagement, involvement in decision-making and satisfaction and adapting to any changes in the results, with clear processes for acting on issues identified
- Plans to engage the contract workforce in deciding the most important workplace issues to address
- Ensuring new workers are informed of their right to join a trade union
- Monitoring of employee engagement rates (by protected characteristic) and, where necessary, the development of actions to ensure all voices are heard across the diversity of the workforce
- Employment contracts that reflect actual hours worked; steps taken to ensure employees understand their contracts and have the ability to review and adjust them if actual hours regularly exceed contracted hours
- Activities that support an environment where staff are educated about, and feel empowered to, address their physical wellbeing
- Activities that support an environment where staff are educated about and feel empowered to report and address bullying and harassment
- Activities to cascade good practice on fair working conditions throughout the supply chain
- Offer a pay and leave entitlement to all eligible staff who become kinship carers, ideally equivalent to statutory adoption pay and leave
- Payment of more than the National Minimum Wage or National Living Wage (as appropriate) to the contract workforce
- Monitoring and reporting of gender and ethnicity pay gaps and plans to address them where necessary
- Entitlement to sick pay for the contract workforce, with provision in place for any staff who do not meet the earnings threshold for statutory sick pay, payment of sick pay from day one of absence and payment of staff on the contract workforce who are off sick a replacement income of 100% of their usual earnings for as long as possible
- Plans for an appropriate income replacement policy for staff who are required to spend time away from work to care for a sick dependent or close relative
- Understanding of in-work progression issues affecting the market, industry or sector relevant to the contract, and in the supplier’s own organisation and those of its key sub-contractors
- Measures to support in-work progression to help people in the contract workforce, to move into higher paid work by developing new skills relevant to the contract
- Support for the contract workforce by providing career advice, and providing opportunities for staff working on the contract with in-work progression career development into known skills shortages or high growth areas
- Support for educational attainment relevant to the contract, including training schemes that address skills gaps and result in recognised qualifications
- Volunteering opportunities for staff
- Understanding of the modern slavery risks and issues affecting the market, industry, sector or country (of origin or of source) relevant to the contract, and the workforce in the supplier’s own organisation and those of its key subcontractors
- Measures to identify, mitigate and manage modern slavery risks relating to the contract and how these will be implemented
- Outline policies and practices to be applied to or put in place for the contract to mitigate and manage modern slavery risks, including: Pre-employment checks, recruitment practices. Workplace conditions, safeguarding plans and processes in place and regular monitoring with relevant groups considered, which may include sampling
- How these flow down the supply chain and are monitored Illustrative examples include reporting, site visits, audits, etc.
- How to ensure business decisions re: price/cost, short lead times, payment timescales do not create modern slavery risks in the supply chain
- How the supplier will work with NGOs, trade unions or other businesses to address modern slavery risk
- Means of influencing staff, suppliers, customers, communities and/or any other appropriate stakeholders with respect to modern slavery risks relating to the contract
-
Mission: Kick start economic growth. To secure the highest sustained growth in the G7 - with good jobs and productivity growth in every part of the country making everyone, not just a few, better off.
Policy Outcome 2: Skills for growth: Supporting growth sectors and addressing skills gaps.
- Understanding of employment and relevant skills issues, and of the education and training issues relating to the contract. Illustrative examples: demographics, skills shortages, new opportunities in high growth sectors, geographic/local community and skills/employment challenges
- Support for educational attainment relevant to the contract, including training schemes that address skills gaps and result in recognised qualifications
- Activities to support relevant sector related skills growth and sustainability in the contract workforce. Illustrative examples: careers talks, curriculum support, literacy support, safety talks and volunteering
-
Mission: Kick start economic growth. To secure the highest sustained growth in the G7 - with good jobs and productivity growth in every part of the country making everyone, not just a few, better off.
Policy Outcome 3: Resilient, innovative and flexible supply chains: Support economic growth through enabling resilient businesses, opportunities for small businesses and voluntary, community and social enterprises
- Activities to identify opportunities to open up sub-contracts under the prime contract to a diverse range of businesses, including new businesses, entrepreneurs, start-ups, SMEs, VCSEs and mutuals
- Plans for engaging a diverse range of businesses in engagement activities prior to appointing subcontractors (including activities prior to award of the main contract and during the contract term)
- Activities that demonstrate a collaborative way to work with a diverse range of businesses as part of the supply chain
- Advertising of supply chain opportunities openly and to ensure they are accessible to a diverse range of businesses, including advertising all subcontracting opportunities on Contracts Finder
- Ensuring accessibility to contracting and subcontracting opportunities for disabled business owners and employees
- Measures for making facilities used in the delivery of the contract available for community groups, education or training
- Measures to engage users and communities and build relationships to increase community integration build trust and influence how the contract is delivered
- Collaborating with anchor institutions and community groups to make facilities available for education, training or community events
-
Mission: Make Britain a clean energy superpower: To cut bills, create jobs and deliver security with cheaper, zero-carbon electricity by 2030, accelerating to net zero
Policy Outcome 4: Sustainable procurement practices: Reducing carbon footprints, minimising waste, and promoting the use of clean energy and green technologies.
- Understanding of opportunities for additional environmental benefits delivery in the performance of the contract, including working towards net zero carbon emissions and use of clean energy and green technologies
- Collaborative ways of working with the supply chain to deliver additional environmental benefits in the performance of the contract, including working towards net zero carbon emissions and use of clean energy and green technologies
- Delivery of additional environmental benefits through the performance of the contract, including working towards net zero carbon emissions and use of clean energy and green technologies
- Understanding of how to influence staff, suppliers, customers, communities and/or any other appropriate stakeholders through the delivery of the contract to support climate and nature protection and improvement
- Activities to reconnect people with the environment and increase awareness of ways to protect and enhance it
-
Mission: Break down barriers to opportunity: By reforming our childcare and education systems, to make sure there is no class ceiling on the ambitions of young people in Britain
Policy Outcome 6: Employment and training: For those who face barriers to employment
- Understanding of employment and skills issues, and of the skills and employment shortages of high growth sectors relating to the contract
- Creation of employment opportunities particularly for those who face barriers to employment, such as prison leavers, care leavers and/or who are located in deprived areas, and for people in industries with known skills shortages or in high growth sectors
- Delivery of training schemes and programmes to address any identified skills gaps and under-representation in the workforce for the contract (e.g. prison leavers, care leavers, kinship carers, disabled people)
- Collection of the views and expertise of disabled people and their representative organisations on successfully supporting disabled employees or applicants
- Offering a range of quality opportunities with routes of progression if appropriate, e.g. T Level industry placements, students supported into higher level apprenticeships.
- Working conditions which promote an inclusive working environment and promote retention and progression
- Understanding of the issues affecting inequality in employment, skills and pay in the market, industry or sector relevant to the contract, and in the supplier’s own organisation and those of its key sub-contractors. Measures to tackle inequality in employment, skills and pay in the contract workforce
- Inclusive and accessible development practices, including guidance for line managers on recruiting, managing and developing people with a disability or health condition
-
Mission: Break down barriers to opportunity: By reforming our childcare and education systems, to make sure there is no class ceiling on the ambitions of young people in Britain
Policy Outcome 7: Creating a pipeline of opportunities: For the contract workforce, reducing barriers to entry for under-represented groups.
- Understanding of the issues affecting the development of new skills by target cohort
- Understanding of the underlying factors affecting improvements to reduce barriers to entry and training schemes for the target cohort(s) related to the contract workforce
- Other measures to offer development opportunities for the target cohort(s) in the contract workforce
- Advertising, promotional and outreach activities designed to raise awareness of the offer to reach the target cohort
- Creation of outreach activities to create a pipeline of employees for the future contract delivery
- Content of the outreach activity is designed to suit the target cohort
- Advertising, promotional and outreach activities designed to raise awareness of the offer to reach the target cohort
-
Mission: Build an NHS fit for the future: That is there when people need it; with fewer lives lost to the biggest killers; in a fairer Britain, where everyone lives well for longer.
Policy Outcome 8: Increasing productivity through physical and mental wellbeing: In the supply chain and communities in the relevant area.
- Understanding of issues relating to health and wellbeing, including physical and mental health, in the contract workforce
- Understanding barriers to access to health and social care services or employment opportunities e.g. digital inclusion
- Actions to invest in the physical and mental health and wellbeing of the contract workforce
-