5 months ago
Base Salary
$213k - $263k/yr
Responsibilities
- Architect and develop efficient, high-performance ML runtime and serving systems for onboard autonomous vehicle compute and large-scale offboard data centers.
- Lead integration and feature development for ML inference runtimes across onboard and offboard environments.
- Balance real-time latency and memory constraints with high-throughput and highly concurrent serving requirements.
- Drive migration of ML workloads toward a JAX-native runtime architecture by extending and modifying ML compilers and runtimes.
- Collaborate with perception, planner, and research teams to analyze workloads and apply hardware-aware compute optimizations.
- Build profiling and benchmarking tools to identify bottlenecks across the end-to-end ML software stack.
Requirements
- Bachelor’s or master’s degree in computer science, electrical engineering, deep learning, or a related field.
- At least five years of professional software engineering experience building, scaling, or maintaining ML systems and infrastructure.
- At least five years of production programming experience in C++.
- At least three years of production experience in Python and major deep learning frameworks such as PyTorch or JAX.
- Experience optimizing ML software for GPUs, TPUs, or custom silicon.
- Experience building low-latency, highly concurrent distributed backend systems.
- Preferred: PhD in computer science, electrical engineering, deep learning, or a related field.
- Preferred: experience modifying ML compilers, runtimes, or inference engines such as TensorRT, ONNX Runtime, OpenXLA/PjRT, or TVM.
- Preferred: experience building or scaling LLM serving systems, including distributed inference and performance optimization.
- Preferred: experience with custom kernel development using CUDA, CUDA Tile, Triton, JAX, or Pallas.
- Preferred: experience architecting unified serving APIs and optimizing tensor buffer management, including zero-copy data transfer and shared memory, for multi-model inference pipelines.
Benefits
- Hybrid work arrangement.
- Full-time position across U.S. locations.
- Eligibility for discretionary annual bonus, equity incentive plan, and company benefits program.
Categories
About Waymo
Waymo develops the Waymo Driver, a full-stack autonomous driving system, and operates the Waymo One robotaxi service that offers paid, driverless rides in select U.S. cities. The company monetizes through ride-hailing fares and partnerships integrating its technology on multiple vehicle platforms. Founded in 2009 as Google’s self-driving project, Waymo is headquartered in Mountain View and is an Alphabet subsidiary, with over 10 million rider-only trips and 100+ million autonomous miles on public roads.