Machine Learning Engineer

Machine Learning Engineer – On-Device Health Monitoring

Cambridge (1 day a week)

Up to £80,000 + Equity + Benefits

About the Role

We’re working with a pioneering health-tech start-up that’s transforming the way we measure human health through sound. Their mission is to create the world’s leading foundation model for turning sound into health insights — enabling preventative health monitoring through devices people already own.

They’re now looking for a Machine Learning Engineer to build and optimise on-device ML models for health and biosignal monitoring, helping take their technology from proof of concept to a production-ready product.

You’ll be at the forefront of developing models that run efficiently on constrained devices, working closely with the CTO on design, optimisation, and deployment. This is a hands-on technical role that offers full exposure to the early-stage startup experience — from prototyping and experimentation to strategic product decisions.

Key Responsibilities

• Develop, optimise, and deploy machine learning models for on-device health monitoring.
• Experiment with architectures and apply techniques such as quantisation, pruning, and compression to improve efficiency.
• Collaborate with cross-functional teams to take research prototypes into production-ready systems.
• Contribute to broader technical and product discussions, including data collection, validation, and feature development.
• Take ownership of projects, working autonomously while supporting the wider engineering team.

What We’re Looking For

• Ph.D. or Master’s degree in Computer Science, Machine Learning, Information or Biomedical Engineering (or similar).
• Strong experience with deep learning frameworks (PyTorch/TensorFlow) and Python development.
• Proven background in on-device ML (TinyML) using frameworks such as TensorFlow Lite, ExecuTorch, or TVM.
• Solid understanding of model optimisation for constrained hardware environments.
• Ability to write clean, maintainable, and well-tested code in a collaborative setting.
• Curiosity, adaptability, and enthusiasm for working in a fast-paced, early-stage environment.
• Experience working with time-series data such as audio or biosignals.
• Background in biomedical or signal processing.
• Experience writing production-level code or integrating models with embedded systems.
• Previous startup experience or exposure to medical device development.