Case Studies | Healthcare & Life Sciences

From laptop to cloud

SageMaker Model Construction IW Build

About

A Healthcare & Life Sciences business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The challenge had three focus areas.

Breaking out of local-only development

The model had been built and run on local machines. That was fine for early research but placed a hard ceiling on scale and on how much of the AWS ecosystem the team could use. Moving into SageMaker was about lifting that ceiling.

Handling 13TB of data

The client deal with roughly 13TB of data. Storing and working with that volume securely, and making it available to training and inference, needed a durable cloud data store rather than local disks.

Retraining and self-sufficiency

An one-off deployment was not enough. The team needed an architecture that could support future retraining, and they needed to be confident operating it themselves rather than depending on the delivery partner.

Solution

The engagement followed Cloud Combinator's Cloud Accelerator, a staged programme that moves from understanding the product to delivering a working solution in the client's own AWS account, with best practices and hands-on upskilling built in along the way.

13TB

Research data given a secure, scalable home on Amazon S3

1

SageMaker inference endpoint standing up the model for on-demand use

Retrain-

Architecture set up to support future model retraining

By the numbers:

  • 13TB - Research data given a secure, scalable home on Amazon S3
  • 1 - SageMaker inference endpoint standing up the model for on-demand use
  • Retrain- - Architecture set up to support future model retraining
Changes

The project was accepted when the client's model was standing and usable in SageMaker, proving AWS as a suitable environment to continue developing the product, with the internal tech lead signed off as competent to carry it forward.

  • Off the laptop, onto the cloud — The model that had only ever run locally now runs in SageMaker, lifting the ceiling on scale and opening up the wider AWS toolset.
  • Data at scale — Around 13TB of research data was given a secure, durable home on Amazon S3, available to both training and inference.
  • Built to retrain — The architecture was set up so the client can retrain future models on the same foundation rather than starting from scratch.
  • A team that can carry it forward — A dedicated immersion day and a full walkthrough left the client's data scientists and ML engineers able to operate and extend the environment independently.
  • Handover — The engagement closed with the model deployed and tested, its usage demonstrated, and the internal tech lead signed off under the Cloud Accelerator acceptance process.

With their model running in SageMaker and an architecture ready for retraining, the client moved from local experimentation to a scalable cloud footing for their machine learning, positioned to grow their drug-discovery work on AWS.

AWS Stack

Amazon SageMaker

For building, deploying and serving the model behind a real-time inference endpoint.

Amazon S3

For secure, durable storage of the roughly 13TB of research data and model artefacts.

Amazon SageMaker Studio Notebooks

For a hands-on development environment for the client's team.

Amazon SageMaker Model Monitor

For keeping watch over the deployed endpoint.

AWS Identity

And Access Management for least-privilege access to data and services.

YOU MIGHT LIKE

Related success stories

View all case studies

Case Studies | Insights

Utilising Language Recognition, Speed, and Enhanced Security to Make Social Media a Force for Good

  • Here, we take a detailed look at how the Cloud Combinator team collaborated with another cutting-edge AI service provider that provides intelligent systems to “make social media more social” for brands and users alike.
  • Arwen AI is a UK-based startup specialising in AI solutions to manage and enhance brands’ social media interactions. Founded in 2020 by Matt McGrory, Dr. David Cole, and Joel Bailey, Arwen. AI focuses on using AI to automatically detect and remove spam, toxic comments, and other unwanted content from social media platforms.
  • The team at Arwen have three core products. ‘Moderate’ is focused on identifying and removing toxic content from social media channels. ‘Engage’ helps brands identify and engage with meaningful conversations on social media, and ‘Customize’ allows brands to apply bespoke algorithms to their channels - creating an even more effective moderation and engagement.
Read more
CONTACT US

Ready to turn AI into impact?

We'll help you spot the highest-value opportunities, reduce risk around your first AI initiative, and define a clear path to results from day one.

Why talk to us:

Outcome-driven recommendations

AWS-recognised delivery expertise

Risk-aware AI adoption

Clear next step, not a sales pitch

Start with a focused 20-minute conversation about your goals — no pressure, no commitment.

We use cookies

This website uses cookies to enhance user experience and to analyze performance and traffic on our website.

See our Privacy Policy for details.