Overview
Cloud Combinator helps health and life sciences teams establish the infrastructure and delivery process for model training on AWS. The service supports a customer-defined model, dataset and research or operational objective.
What we deliver
- Review the training workload, data access, compute needs, budget and acceptance criteria.
- Design and configure the agreed AWS training environment. This may use Amazon SageMaker and SageMaker HyperPod with suitable compute where required and available.
- Implement data and training pipelines with agreed access controls, versioning and reproducibility measures.
- Configure experiment tracking, monitoring, checkpoints and operational procedures appropriate to the training design.
- Run and document the agreed training or pipeline validation work.
- Support evaluation against customer-approved baselines and provide infrastructure documentation and handover.
Scope and prerequisites
The customer provides authorised datasets, a scientific or model owner, an approved model and training plan, evaluation criteria and a compute budget. We agree which dataset preparation, training, evaluation and deployment tasks are included before work starts.
This package covers the agreed engineering and infrastructure work. Designing and training a new foundation model from scratch requires a separately validated scientific plan, data rights, evaluation method and compute budget. Model performance, research results and ownership rights depend on the selected data, models, licences and contract terms.
The service does not provide clinical validation, medical device certification or approval for diagnostic use. The customer retains responsibility for intended use, quality review and applicable governance requirements.
Scope, delivery dates, acceptance criteria, support coverage and price are agreed in the statement of work and private offer. Service charges are billed through the selected AWS Marketplace dimensions. Customers pay separately for AWS infrastructure, model usage and any third-party subscriptions or licences. Ongoing managed operations are included only when stated in the offer. Any AWS funding depends on eligibility and approval and is confirmed separately. Outcomes depend on the agreed inputs, data and evaluation criteria.
Contact Cloud Combinator to assess the workload and define the training infrastructure scope.
Highlights
- Create an AWS training environment and repeatable pipelines for an agreed HCLS workload.
- Configure access controls, experiment tracking, monitoring and reproducibility measures.
- Validate the agreed engineering outputs against customer-defined training and evaluation criteria.
Details
Pricing
Custom pricing options
How can we make this page better?
Legal
Content disclaimer
Support
Vendor support
Contact Cloud Combinator at hello@cloudcombinator.ai or +44 20 3588 2584.
Before purchase, Cloud Combinator helps you assess suitability, scope and prerequisites. We respond to enquiries received through the listing within two business days.
After private offer acceptance, we contact you or provide next steps within two days, unless the offer specifies another arrangement. During delivery, we provide configuration guidance, troubleshooting and handover support for the agreed scope. Support hours, the post-handover support period and any response targets are specified in the statement of work and private offer. Use the support contact shown on this listing and the fulfilment page for service issues and refund requests; refund terms are set out in your offer.