Staff ML Engineer - Embodied AI Evaluation Foundations

GM•Sunnyvale, CA

8h•Remote

About The Position

At General Motors, our product teams are redefining mobility. Through a human-centered design process, we create vehicles and experiences that are designed not just to be seen, but to be felt. We’re turning today’s impossible into tomorrow’s standard —from breakthrough hardware and battery systems to intuitive design, intelligent software, and next-generation safety and entertainment features. Every day, our products move millions of people as we aim to make driving safer, smarter, and more connected, shaping the future of transportation on a global scale. Are you passionate about accelerating the future of autonomous driving? Join the Embodied AI team at General Motors. Our team is developing and deploying machine learning solutions that support safe and reliable autonomous vehicle behavior across real-world scenarios. The Evaluation Foundations team—part of Embodied AI’s Scaling Foundations—solves critical evaluation challenges in autonomous vehicle development. We engineer high-performance tools that identify top-performing models and partner with data-intensive ML teams to drive rapid innovation. In this role, you will develop introspection and evaluation tools capable of processing billions of examples to unlock maximum value from our large-scale datasets. Joining a high-impact team of engineers and ML scientists, you will leverage advanced AI to advance L2, L3, and L4 autonomous vehicle technology and directly shape the safety, reliability, and scalability of next-generation systems. As a Staff Engineer, you will serve as a key individual contributor focused on measuring and visualizing AV model performance. You will collaborate across the stack and with cross-functional stakeholders to design, build, and iterate on evaluation tools used by Embodied AI and adjacent GM AV teams.

Requirements

Familiarity and experience with key technologies across the stack: Frontend: React/TypeScript, WebGL/WebGPU (for 3D sensor visualization), Streamlit, Jupyter Notebooks Backend: Python, Node.js, high-throughput data streaming Data/Infra: Spark (for stream processing), BigQuery, Kubernetes.
Experience shipping production software and iterating quickly in a "startup within an enterprise" environment.
Strong communication skills and the ability to collaborate effectively with cross-functional engineering partners.
Bachelor’s, Master’s, or PhD in Computer Science, a related technical field, or equivalent practical experience.

Nice To Haves

Previous experience in Robotics or Autonomous Driving.

Responsibilities

Build and refine high-quality evaluation signal and introspection tools to shorten the experiment path toward optimal models.
Develop and maintain visualization tools and metrics presentation within our core model evaluation loop.
Enable ML teams to introspect model behavior and drive actionable, data-driven decisions with minimal manual intervention.
Provide technical leadership through design and code reviews, establish evaluation tooling best practices, and collaborate closely with Data (Consumption/Mining/Quality), Infra Foundations, and Simulation/On-Road Validation teams to align offline evaluation with real-world vehicle behavior.
Work closely with modeling and data scaling teams building our Compound AI driving models to design and implement large-scale evaluation workflows—utilizing model-based metrics, end-to-end simulation, and tooling that connects evaluation signals back to data selection, training, and launch decisions.
Drive a cohesive evaluation flywheel: better signal → better data and training decisions → better models → better signal.