San Francisco startup building autonomous systems for physical work in industrial environments
Member of Technical Staff: Evaluations
You'll spend your days designing and running the evaluation frameworks that tell us whether our robots actually work. Your benchmarks will shape what gets deployed to factory floors—wrong metric, wrong behavior, real consequences. We're a small team with significant funding and hard problems that demand rigorous measurement, not leaderboard chasing.
What they're looking for
- Strong Python for building reproducible evaluation pipelines and data infrastructure
- Experience with ML systems evaluation beyond standard accuracy metrics—latency, robustness, edge cases
- 1+ years in robotics, hardware, or physical systems; understanding that simulation gaps matter
- Comfort working on-site alongside robots and engineers who debug from observed failures
- Familiarity with statistical rigor: confidence intervals, variance analysis, knowing when a number lies