Atoms
Safety Validation Lead, Scenarios
$182K–$231K
San Francisco, CA +1 · Full-time · Posted Sep 1, 2026
- Location
- San Francisco, CA
San Francisco, California, United States - Experience
- 8+ years; hands-on experience in safety validation, verification, or test engineering.
About the job
Owns the safety-relevant scenario catalog, tooling, and coverage argument used to validate automated-vehicle systems and support the safety case.
What you'll do
- Define scenario relevance and coverage for operating-domain slices; maintain a coherent catalog and identify gaps or staleness.
- Build and maintain tooling for scenario queries, log-based extraction, criticality analysis, and catalog coverage; own regression scenarios.
- Adapt published crash-avoidance protocols, define scenario execution and evidence limits, and defend the combined coverage argument.
What they ask for
- 8+ years in hands-on safety validation, verification, or test engineering for automated vehicles, ADAS, or another safety-critical domain.
- Built or substantially shaped a scenario catalog for a defined operating domain and defended its sufficiency.
- Hands-on with crash-avoidance protocols such as Euro NCAP Crash Avoidance protocols in the 2026 series, the ADAS component of US NCAP, or equivalent.
- Hands-on ASAM OpenSCENARIO and OpenDRIVE; ISO 21448 (SOTIF) and ISO 34502; strong Python and direct work with large vehicle-log datasets.
Nice to have
- Proving-ground or closed-course test execution, including instrumented targets and test equipment.
- Experience in adversarial scenario search, safety-case evidence, traffic safety research, or validation infrastructure.
Pay
$182,000 - $231,000 per year (base salary)
Tools
ASAM OpenSCENARIO, OpenDRIVE, ISO 21448 (SOTIF), ISO 34502, Python
AI focus
Use and shape AI tooling for scenario mining and categorization, criticality assessment, parameter-space search, documentation, log-event classification and clustering, scenario-variant testing, catalog gap checks, and mapping published protocols to the company taxonomy; generated scenarios require human verification and traceable justification.
Model-written summary · the original posting is authoritative