Machine Learning Engineer, Compiler
Wayve is a London-headquartered embodied-AI company developing and licensing mapless, vehicle-agnostic driving software for assisted, automated, and robotaxi applications.
About Wayve
Wayve Technologies Ltd. develops the Wayve AI Driver, an end-to-end, data-trained software platform that runs on onboard vehicle compute and native sensors. It is designed for OEM integration across L1 driver assistance through L4 automated driving, without HD maps.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own the ML compilation pipeline from model checkpoint to deployable bundles for NVIDIA and Qualcomm targets. You will build compiler passes and scalable infrastructure, validate accuracy and latency, collaborate on compilability, benchmark changes, set technical direction, and mentor on compiler design.
Requirements
- Experience building or extending ML compilation or graph-lowering pipelines
- Understanding of capture, decomposition, precision assignment, and legalisation
- Proficiency with MLIR, ONNX, TensorRT, Qualcomm QNN, or PyTorch export and capture
- Experience with quantisation, precision typing, PTQ integration, and accuracy debugging
- Strong Python skills
- Experience with multi-target compilation or graph partitioning
- Ability to evaluate correctness and performance trade-offs
Responsibilities
- Own the ML compilation pipeline from checkpoint to deployable bundle
- Design and implement compiler passes with accuracy and latency gates
- Build compilation infrastructure across platforms, architectures, and SoCs
- Partner with model and training engineers on compilability
- Build regression testing and benchmarking across releases
- Extend precision typing and graph-splitting logic
- Set technical direction and mentor on compiler design