Senior ML Engineer: AI Performance & Edge Deployment

AI Startups UK; Greater London; Hybrid; GBP 90,000 - 140,000; Full time

Job summary

Wayve is seeking a Senior Machine Learning Engineer to own end-to-end model releases for production systems with tight latency and resource constraints. You will drive development from training to on-vehicle deployment, collaborating with performance and inference teams to meet product needs.

You will iteratively improve PyTorch models, apply optimization techniques like quantisation and distillation, and ensure deployments align with real-world constraints.

Qualifications

• Proven experience improving performance in production systems with tight constraints (latency, memory, bandwidth, power/thermal, or cost).
• Strong hands-on experience training and iterating on deep learning models in PyTorch (not just high-level tooling).
• Proficiency with stack/toolchain such as TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL and ability to learn adjacent frameworks quickly.
• Comfort operating at multiple levels of abstraction—from high-level model behavior to low-level kernel/runtime execution.
• Familiarity with model optimisation concepts such as quantisation and distillation (hands-on is preferred).
• Ability to reason across model behavior and runtime/latency implications.

Responsibilities

• Own end-to-end delivery of model releases, from initial requirements through training, evaluation, iteration, and final readiness for deployment.
• Train and iterate on PyTorch models with a strong experimental approach (hypothesis‑driven iteration, ablations, clear evaluation criteria).
• Debug and improve model performance using strong analytical skills—identifying regressions, root‑causing issues, and proposing fixes.
• Apply optimisation techniques (e.g., quantisation and distillation) and understand trade-offs and when to use them.
• Collaborate cross‑functionally with adjacent ML and performance engineering teams to hand off models and align on bottlenecks and priorities.
• Communicate clearly with stakeholders to align on delivery timelines and readiness criteria.

Skills

Production performance

PyTorch

Model optimisation

Quantisation

Distillation

Tools

PyTorch

TensorRT

CUDA

Triton

OpenCL

QNN

Job description

Wayve is seeking a Senior Machine Learning Engineer to own end-to-end model releases for production systems with tight latency and resource constraints. You will drive development from training to on-vehicle deployment, collaborating with performance and inference teams to meet product needs.

You will iteratively improve PyTorch models, apply optimization techniques like quantisation and distillation, and ensure deployments align with real-world constraints.