Senior ML Systems Engineer - AI Evaluation Foundations

General Motors•Washington, DC

4d•$144,700 - $261,300•Remote

About The Position

As a Senior Engineer in the Embodied AI Scaling Foundations organization, you will be a key technical contributor on the team that measures and visualizes AV model performance. You will work across the stack to design, implement, and iterate on evaluation and introspection tools used by Embodied AI and adjacent GM AV teams. In this role you will: Build and improve high-quality evaluation signal and introspection tools that help shorten the experimental path towards the best model. Develop and maintain visualization and metrics presentation within our model evaluation loop. Help teams introspect model behavior and reach actionable next steps with fewer manual steps. Participate in design and code reviews and work with Data, Infra, and validation teams to connect offline evaluation with real-world behavior. You will collaborate closely with modeling and data scaling teams working on our Compound AI driving models to design and implement evaluation workflows at scale with model-based metrics, end-to-end simulation, and tooling that connects evaluation signals back to data, training, and launch decisions. Your work contributes to a cohesive evaluation flywheel: better signal → better data and training decisions → better models → better signal.

Requirements

3+ years of relevant industry experience
Familiarity and experience with at least some of the following key technologies: Backend: Python, node.js, high-throughput data streaming.
Frontend: React/TypeScript, WebGL/WebGPU (for 3D sensor visualization), Streamlit, Jupyter notebooks.
Data/Infra: Spark for stream processing, BigQuery, Kubernetes.
Strong communication skills and ability to collaborate effectively across engineering partners.
Bachelor's degree in Computer Science or related field or equivalent experience

Nice To Haves

Previous experience in Robotics or Autonomous Driving
5+ years of relevant industry experience
Master's or PhD degree in Computer Science or related field or equivalent experience
Experience shipping production software and iterating quickly in a "startup within an enterprise" environment.

Responsibilities

Build and improve high-quality evaluation signal and introspection tools that help shorten the experimental path towards the best model.
Develop and maintain visualization and metrics presentation within our model evaluation loop.
Help teams introspect model behavior and reach actionable next steps with fewer manual steps.
Participate in design and code reviews and work with Data, Infra, and validation teams to connect offline evaluation with real-world behavior.
Collaborate closely with modeling and data scaling teams working on our Compound AI driving models to design and implement evaluation workflows at scale with model-based metrics, end-to-end simulation, and tooling that connects evaluation signals back to data, training, and launch decisions.