Senior Software Engineer/Data Scientist, Large Model Evaluation

Join the Large Model Evaluation team to design and implement novel evaluation metrics and sampling strategies for driving trajectories produced by ML models. Use creative simulation approaches to quantify driving performance of generative AI systems, identify edge cases, and deliver reliable performance insights to guide model development and deployment. Build end-to-end data pipelines for signal discovery, labeling, feature extraction, and metric computation from large-scale simulations; perform data analysis to diagnose regressions and root causes. Collaborate with software engineers and researchers to scale evaluation tools across large ML models and real-world driving contexts. Requirements include 5+ years in quantitative software engineering, proficiency in Python or C++, experience building data pipelines, system evaluation, and productionized tooling; knowledge of transformer architectures and ML fundamentals; familiarity with frameworks such as JAX or TensorFlow is a plus; experience with simulation, robotics, or autonomous vehicles is preferred.