Software Engineer, Evaluation Infrastructure
Core
Building algorithms and tooling to evaluate autonomous vehicle performance across development stages using simulation and real-world data.
Role type
Software Engineer, Evaluation Infrastructure
Builds
Evaluation pipelines, query services, and metrics infrastructure for autonomous driving systems.
Domain
Autonomous vehicles / Physical AI / Simulation
Deliverable
production ML models | infrastructure
Required skills
Python, software engineering fundamentals, statistical analysis, data pipeline development, high-availability service development, code testing and structuring
Preferred skills
ETL pipelines, distributed computing, cloud job orchestration, monitoring and instrumentation, complex ML model evaluation
Technologies
Python, Waabi World (simulation engine)
Responsibilities
Develop tooling and pipelines for statistical analysis of driving performance; Implement metrics and tags for model performance understanding; Maintain high-availability query services for low-latency data analysis; Work with large datasets from real-world driving and simulation; Champion engineering excellence with tested code; Assist in project roadmap planning and delivery.
