Staff Software Engineer, Inference, ML Platform

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, model development, debugging and evaluation, deployment, and monitoring. These efforts have resulted in making machine learning more accessible to teams at Waymo, including Perception, Behavior Prediction, Planner, Routing, Maps and Research, ensuring greater degrees of consistency and repeatability, and addressing the "last mile" of getting models into production and managing them once they are in place. We work with machine learning experts in all parts of the company and our collaborators across Alphabet. You will focus on developing large-scale and efficient inference solutions for Waymo. This is crucial to the development of Waymo Foundation Models for driving including evaluation, auto-labeling and distillation.

You will focus on developing large-scale and efficient inference solutions for Waymo. This is crucial to the development of Waymo Foundation Models for driving including evaluation, auto-labeling and distillation.

At a minimum, we'd like you to have:

• B.S. in Computer Science, Math, or equivalent real-world experience
• 2+ years of experience as a technical lead
• 5+ years working with high-scale distributed or ML inference systems
• Understanding of machine learning fundamentals and experience with popular ML frameworks such as JAX, PyTorch, or TensorFlow
• Experience with building scalable inference platforms for real-time and batch processing
• ML accelerator profiling, model inference for LLMs, and designing production-grade systems
• Lead software development projects using C++ or Python and deploying on cloud platforms such as AWS, Azure, or GCP

It's preferred if you have:

• MS in Computer Science, Math, or equivalent real-world experience
• Experience with multi-threaded and stream-based programming models
• Prior experience scaling model inference to multiple accelerators
• Prior experience on ML compiler optimization such as TVM or XLA
• Previous experience deploying machine learning models for computer vision, natural language processing, or recommendation systems

#LI-Hybrid