Machine Learning Engineer – Edge Deployment / Integration

Remote (UK) | Client Travel

Building models is one thing.

Getting them to run reliably on real hardware is where it gets interesting.

You’ll take advanced ML models and make them work in constrained, real-world environments — often on edge devices where compute, power and latency are all limited.

This is applied ML engineering:

Deploying models onto embedded / edge hardware

Optimising inference (TensorRT, quantisation, compression)

Working closely with customers to integrate into real systems

The work is hands-on, varied and close to deployment — not stuck in experimentation.

You’ll likely bring:

Strong experience with PyTorch / TensorFlow

Experience deploying models to edge or hardware-constrained systems

Familiarity with tools like TensorRT or similar optimisation frameworks

Ability to work with customers and adapt solutions to real-world constraints

Remote (UK) + client site work

Eligible for SC/DV

If you enjoy making ML actually work outside of ideal environments - this is worth a look.