Senior ML Performance Engineer, Inference Optimisation

Highlights

• Optimize large transformer models to run on low-power in-vehicle compute.
• Turn research models into reliable production systems for autonomous driving.
• Find bottlenecks across model graphs, execution and memory movement.

What they offer

• Salaries benchmarked against the market annually
• Meaningful equity sharing in long-term success
• Relocation support and visa sponsorship where applicable
• Hybrid working with core hours and hands-on vehicle workshops and labs
• Learning and development budgets for training and conferences
• Comprehensive benefits including health insurance, dental, enhanced parental leave, pension and wellbeing support

Ideal candidate

Hands-on systems thinker who loves squeezing performance from constrained real-world systems. Collaborative, ownership-driven and excited by autonomous driving in a fast-moving, unstructured environment.

Requirements

• Experience improving performance in production or production-adjacent systems with latency, memory, bandwidth, power, thermal or cost constraints
• Strong hands-on experience with at least one relevant stack such as TensorRT, CUDA, Qualcomm QNN, Triton or OpenCL
• Comfortable working from high-level model behaviour down to kernel/runtime-level execution
• Strong software engineering fundamentals including debugging, profiling, testing and maintainable code
• Clear communication and collaboration across ML, systems and deployment teams