🛠 Tech Stack

💼 About This Role

You'll optimise ML inference for edge accelerators and GPUs, driving the team's focus on running large transformer models efficiently on low-cost, low-power devices. Your work directly enables Wayve's first driving product by turning models into reliable production systems on in-vehicle compute. This is a hands-on role contributing to high-impact, early-stage projects.

🎯 What You'll Do

• Profile and pinpoint bottlenecks across the full inference stack.
• Implement optimisations in compilers, runtimes, and kernels.
• Build robust benchmarking and regression testing for performance.
• Optimise for multiple targets (e.g. NVIDIA Orin/Thor, Qualcomm).

📋 Requirements

• Proven experience improving performance in production systems with tight constraints.
• Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, QNN, Triton, OpenCL).
• Comfort operating at multiple levels of abstraction from high-level model behaviour to low-level execution.
• Strong software engineering fundamentals (debugging, profiling, testing, maintainable code).

✨ Nice to Have

• Exposure to embedded or edge deployment of ML models.
• Experience with NVIDIA and/or Qualcomm SoCs and performance tooling.
• Python and C++ proficiency.

🎁 Benefits & Perks

• 🏖️ Hybrid working policy combining office and home time.
• 📈 High-impact projects in autonomous driving.
• 🌍 Diverse and inclusive culture.

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Phone Screen· 60 min
3. 3Onsite Interview (3-4 rounds)· 4 hours