Location
London

Hours
Full Time

Salary
Competitive, commensurate with experience

About the Role
Qureight’s mission is to accelerate clinical trials and ensure breakthroughs in lung and heart disease reach patients without delay. Our AI-powered data and imaging curation platform enables the analysis of clinical imaging and other healthcare data, helping our customers bring treatments to market faster. With offices in Cambridge and London, you will join a multidisciplinary team of clinicians, scientists, and engineers united by an open culture, continuous learning mindset, and a shared mission to help biopharma run faster, smarter trials.

As Qureight scales its AI-driven imaging platform and expands its work with pharmaceutical and clinical partners, we are building the machine learning engineering capability required to train, optimise, and deploy large-scale 3D medical-imaging models reliably. This role focuses on the development, training, optimisation, and inference of state-of-the-art computer vision models applied to volumetric CT data. You will ensure models can be trained efficiently, deployed securely, and operate at scale.

This position sits within the Machine Learning function and works closely with ML Scientists, DevOps, Data Engineering, and Software Engineering teams to turn research models into robust, scalable, and reproducible training and inference workflows.

Key responsibilities include developing robust, scalable and reproducible inference pipelines; deploying models into production using ONNX, TensorRT or similar frameworks; building and optimising scalable machine learning training workflows; optimising data loading, logging, checkpointing and resource utilisation for large-scale model training; acting as a bridge between research and production by translating research into reliable, maintainable and scalable engineering components; supporting cloud-based ML infrastructure such as MLFlow; creating and maintaining CI pipelines for model training, testing and deployment workflows; collaborating with DevOps and infrastructure teams on deployment patterns and infrastructure as code; improving reproducibility, traceability and quality across ML engineering workflows; and identifying risks, communicating trade-offs and proactively improving tooling and processes.

Experience
- Strong Python and PyTorch skills with confidence in model training and inference codebases
- Building, optimising and maintaining ML training and inference pipelines
- Experience with Docker and containerised ML workflows
- Experience with model deployment and optimisation frameworks such as ONNX, TensorRT or similar tools
- GPU-based training, model serving and compute optimisation
- Building and maintaining CI pipelines
- Experience with cloud environments
- Strong knowledge of Linux shells, git and modern Python development tools such as uv, poetry, ruff, black, mypy or ty
- Familiarity with modern development workflows including pull requests, code review, documentation and ticketing
- Strong communication skills and ability to collaborate across ML Science, DevOps, Data Engineering and Software Engineering teams

About you
Detail-oriented and proactive engineer passionate about bridging research and production environments. You thrive in multidisciplinary teams and are committed to delivering scalable, maintainable ML engineering solutions in a regulated and clinical context.

Qualifications
Relevant degree or equivalent experience in computer science, machine learning, engineering or related fields is expected.

Even better if you have
- Experience working with 3D medical imaging, CT data, DICOM, NIfTI or NRRD formats
- Experience deploying models in regulated, clinical, pharmaceutical or healthcare environments
- Experience with infrastructure as code such as Terraform
- Experience with multi-stage Docker containers and secure software supply-chain practices
- Experience with distributed training, large-scale data loading or high-performance computing environments
- Experience supporting research-to-production ML workflows
- Experience with monitoring, observability, model versioning or MLflow-like tooling