ML Compiler Engineer - Embedded Autonomy

Wayve; Greater London; On-site; GBP 120,000 - 160,000; Full time

Job summary

Wayve in London is seeking a Staff ML Compiler Engineer to own the end-to-end ML compilation pipeline from model checkpoint to deployable bundle on NVIDIA TensorRT and Qualcomm QNN targets. You will design passes, extend precision typing, and build scalable infrastructure to support multiple architectures, while collaborating with model and training teams to ensure accuracy and performance.

This role offers deep ownership, hands-on implementation, and impact on embedded hardware in Wayve's

Qualifications

• Built or owned significant parts of an ML compilation or graph-lowering pipeline.
• Deep experience with multi-stage lowering and debugging per-stage failures.
• Strong Python; C++ is a plus; able to work with vendor backends.

Responsibilities

• Own the ML compilation pipeline end-to-end for targeted hardware.
• Design compiler passes with accuracy and latency gates.
• Extend precision typing and graph-splitting for new architectures.
• Collaborate with model and training teams on compilability.
• Build regression and benchmarking to validate changes across releases.

Skills

Python

Compiler design

Cross-functional communication

Tools

MLIR

ONNX

TensorRT

Qualcomm QNN

PyTorch export/capture

Job description

Wayve in London is seeking a Staff ML Compiler Engineer to own the end-to-end ML compilation pipeline from model checkpoint to deployable bundle on NVIDIA TensorRT and Qualcomm QNN targets. You will design passes, extend precision typing, and build scalable infrastructure to support multiple architectures, while collaborating with model and training teams to ensure accuracy and performance.

This role offers deep ownership, hands-on implementation, and impact on embedded hardware in Wayve's