Lead Evaluation Engineer – Scenario Coverage & Datasets (Autonomous Driving)

What you'll do

• Define and maintain the evaluation dataset, coverage model, and scenario taxonomy; identify gaps and report coverage, readiness, confidence, and blind spots.
• Direct scene collection through data mining, simulation, or field capture; set mining priorities and provide requirements and feedback for tooling, labeling, and analytics teams.
• Lead through process and collaboration with QA engineers, and bring forward proposals based on approaches used by other programs, researchers, and vendors.

What they ask for

• 8+ years in software testing, test engineering, validation, or evaluation, including 2+ years owning test or evaluation strategy for a full system rather than a feature area.
• Track record of taking on more, including owning an area end to end, leading or mentoring engineers, and improving team processes.
• Knowledge of coverage concepts such as equivalence classes, parameter spaces, and risk-based prioritization.
• Hands-on SQL and Python for querying and validating metrics data; fluent use of LLMs as a working tool; strong written communication; ability to reason precisely about US road rules and real-world driver behavior or learn quickly.

Nice to have

• Experience hiring QA engineers or working in autonomous vehicles, robotics, ADAS, or another safety-critical domain.
• Familiarity with scenario-based testing standards, data mining or active learning, internal tooling, vehicle dynamics, or LiDAR, radar, and cameras.

Tools

SQL, Python, LLMs, ISO 34503, ISO 34501/34502, ISO 21448, LiDAR, radar

AI focus

Use LLMs for log search, triage, scenario generation, report drafting, and quick analysis scripts; use VLM-assisted retrieval and clustering for driving-data coverage.