Machine Learning Engineer II - Autonomous Driving Performance Evaluation
Core
Design, implement, and own ML metrics and evaluation pipelines to measure, analyze, and systematically improve the performance of May's Autonomous Driving stack through data, metrics, and test suites.
Role type
ML-oriented software engineer (autonomous driving performance evaluation)
Builds
Evaluation and analytics frameworks in production, including dataset slicing, result aggregation, and dashboarding at scale
Domain
Autonomous driving, robotics, machine learning
Deliverable
production ML models
Required skills
Python (NumPy/Pandas), Linux environments, quantitative metrics design, statistical analysis, loss analysis, error mining, data balancing/curation strategies
Preferred skills
Go or C++, experiment tracking tooling (MLflow, W&B), statistical methods for A/B comparison, data mining and curation at scale, visualization tools (Plotly, Grafana, Streamlit)
Technologies
Python, NumPy, Pandas, Linux, MLflow, Weights & Biases, Plotly, Grafana, Streamlit
Responsibilities
Design, implement and own ML metrics and evaluation pipelines spanning offline model evaluation, simulation and on-road performance; Build and maintain test, regression and hillclimbing suites that gate model and stack releases; Drive model improvement through loss analysis, error mining, and data balancing/curation strategies
Seniority
Mid-level, hands-on IC
