Senior/Staff Software Engineer, ML Performance Optimization
Core
Drive ML Performance Optimization initiatives to make ML models enabling autonomous driving fast and efficient.
Role type
Senior/Staff Software Engineer, ML Performance Optimization
Builds
ML Training and Inference performance optimization techniques for VLM, VLA, and Foundational models
Domain
Autonomous driving, Large-scale Foundation models, VLMs, VLAs
Deliverable
production ML models
Required skills
PyTorch, GPU-accelerated inference (TensorRT), profiling tools (NVIDIA Nsight, PyTorch Profiler), Python, C++, model compression techniques
Preferred skills
Large-scale model training or inference platforms experience, leadership skills
Technologies
PyTorch, TensorRT, NVIDIA Nsight, PyTorch Profiler
Responsibilities
Develop and execute a strategic vision for the ML Performance Optimization team; Lead the design, implementation, and operation of cutting-edge ML Training OR Inference performance optimization techniques; Collaborate with x-functional teams to define requirements and align on architectural decisions; Enable engineers in the team to grow their careers by providing technical guidance and mentorship
Seniority
Senior/Staff, hands-on IC with mentorship