Optimize inference for edge accelerators and GPUs to enable efficient execution of large transformer-based models on in-vehicle compute. Focus on profiling, implementing optimizations in compilers and kernels, and building benchmarking tests for production systems. Requires strong experience in ML systems, software engineering fundamentals, and performance optimization under hardware constraints.
Key Highlights
Optimize ML inference for NVIDIA Orin/Thor and Qualcomm platforms
Implement performance improvements across compilers, runtimes, and custom kernels
Collaborate with model developers to make deployment-aware design decisions
Key Responsibilities
Profile inference performance across model graphs, compiler/runtime behaviour, kernel execution and memory movement
Implement and validate optimisations in compilers, runtimes and/or kernels, including fusion, scheduling, and quantisation-aware performance
Build benchmarking and regression tests to track performance across models, devices and software releases
Optimise for edge targets such as NVIDIA Orin/Thor and Qualcomm platforms
Contribute to team tooling, documentation and technical discussions around ML performance
Technical Skills Required
CUDA
TensorRT
ML Compilers
Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.
Benefits & Perks
Market-benchmarked salaries
Equity
Relocation support
Visa sponsorship
Hybrid working
Learning and development budgets
Health insurance
Dental insurance
Enhanced maternity and paternity leave
Retirement or pension
Nice to Have
Experience deploying or benchmarking ML models on embedded or edge devices
Familiarity with NVIDIA and/or Qualcomm SoCs and performance tooling
Python and C++ proficiency
Experience supporting other engineers or contributing to technical direction within a small team
Job Description
Before the detail, here's the challenge you'd help us solve.We build the embodied intelligence that moves real vehicles safely, and the ecosystem a billion machines will run on in the future. Very few people in AI can say this. Every role here, whatever the team, plugs into that.Here’s what this particular role covers.Our ML performance team optimises inference for edge accelerators and GPUs, so large transformer-based models run efficiently on low-cost, low-power in-vehicle compute. We work closely with model, platform and deployment teams to turn research models into reliable production systems for Wayve's driving product.
Want the full job description?
Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn
This is a short excerpt. All rights to the full description belong to its original publisher.
