Machine Learning Engineer, Runtime Optimization

The ML Platform team at Waymo provides a set of tools to support and automate the lifecycle of the machine learning workflow, including feature and experiment management, optimization and monitoring to make our Perception, Planner, Research and Simulation teams better. We require your expertise to help us improve compute performance on both cloud and car. You'll work across the entire ML stack from the system perspective, from efficient deep learning models and model compression.

You will report to the Senior Manager

You will:

• Collaborate with the world-class Waymo ML practitioners in perception, planner, research and simulation to analyze ML workload performance and apply optimization techniques.
• Support the building of tools for benchmarking and optimizing deep learning models
• Contribute to the analysis of ML software stack and model performance.
• Develop an efficient ML runtime system and optimized ML operator libraries for the diverse hardware options on Waymo's platforms.

You have:

• B.S. in CS, EE, Deep Learning or a related field
• 2+ years of industry experience
• Solid C++ programming skills
• Experience developing/using deep learning frameworks (PyTorch, TensorFlow, JAX, etc.)
• Passion developing and optimizing ML software stacks for modern ML accelerator architectures (framework, runtime library, ML compiler, GPU performance/optimization etc)

We Prefer:

• M.S. or PhD in CS, EE, Deep Learning or a related field.
• Experience on ML frameworks, ML compiler and IRs (MLIR, HLO, Triton) or modern ML system architectures and heterogeneous runtime systems/ML inference/serving engine.

#LI-Hybrid