Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Machine Learning Engineer, Performance Tooling role.
Rezi rewrites your resume against Wayve's job description. Free.
Tailor your resume to this Machine Learning Engineer, Performance Tooling role.
Rezi rewrites your resume against Wayve's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Machine Learning Engineer, Performance Tooling posting at Wayve — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Machine Learning Engineer, Performance Tooling posting at Wayve — free, in seconds.
About the Role
Wayve is developing autonomous driving technology for real vehicles. This role focuses on owning the ML compilation pipeline, which is critical for deploying models onto embedded hardware, ensuring accuracy and low latency across various target platforms.
Responsibilities
- Own the ML compilation pipeline end-to-end, from checkpoint to deployable bundle on NVIDIA (TensorRT) and Qualcomm (QNN) targets.
- Design and implement compiler passes with accuracy and latency gates to catch compilation errors before they reach hardware.
- Build scalable compilation infrastructure that supports multiple platforms, model architectures, and SoCs without requiring re-engineering for each new target.
- Collaborate with model and training teams on compilability, establishing regression and benchmarking processes to validate changes across releases.
- Set technical direction and elevate the standard of compiler engineering within the team.
- Extend precision typing and graph-splitting logic for new architectures and SoCs.
- Build regression and benchmarking to validate changes across releases.
- Set technical direction and mentor on compiler design.
Requirements
- Experience building or significantly extending ML compilation or graph-lowering pipelines.
- Understanding of multi-stage lowering (capture, decomposition, precision assignment, legalisation) and ability to debug issues at each stage.
- Experience with quantisation in compilation, including precision typing, PTQ integration, and tracking accuracy loss from compiler transforms.
- Comfortable working with high-level model graphs down to vendor backend constraints.
- Ability to reason about correctness and performance trade-offs at each compiler stage.
- Experience with multi-target compilation or graph partitioning across hardware backends.
Skills
- MLIR
- ONNX
- TensorRT
- Qualcomm QNN
- PyTorch export/capture
- Python
- C++
Location
- Remote
Work Type
- Full-time
Experience Level
- Staff level
About the Company
- Wayve is building autonomous driving technology that runs on real vehicles.