Job Description
Computer Vision / ML Optimisation Engineer - Manchester - £70,000 - £90,000
We’re working with a high-impact UK organisation driving real-time AI innovation across edge and GPU-accelerated systems. As part of a forward-looking expansion into 2026, they’re strengthening their AI deployment capabilities to power faster, leaner model performance at scale. This is a rare chance to shape the tech direction before the team fully scales - ideal for someone who thrives in deep-tech environments where theory meets hardware.
The engineer will join a specialist function focused on refining model performance, optimising inference, and enabling low-latency deployment across diverse compute platforms.
Role Highlights
You'll work on:
– Optimising deep learning models through quantisation, pruning, and fine-tuning
– Evaluating architectures for speed/accuracy trade-offs across devices
– Exporting models for runtime use (e.g. ONNX, TorchScript)
– Supporting research-to-deployment workflows that accelerate iteration
– Helping define a scalable ML pipeline for edge and embedded use
You'll bring:
– Proven experience in CV/ML model optimisation and deployment
– Knowledge of TensorRT, ONNX Runtime or similar inference runtimes
– Hands-on experience with CUDA, low-latency profiling and C++ integration
– Strong command of model export tools and deployment best practices
– A performance-first mindset and confidence in debugging at system level
Why them?
– Strong base salary
– Hybrid working with flexible remote days
– Work at the intersection of research, AI systems, and deployment
– Clear progression as the 2026 expansion builds out
– Contribute to real-world AI acceleration that moves beyond the lab/demo stage
Notes:
Please note this role cannot offer visa sponsorship now or in the future. This is a hybrid role from Manchester city centre (2 days per week), candidates not based within a commutable distance will not be considered.