Software Verification & Validation Engineer in Santa Clara, California at PlusAI Inc

Performance Metrics Definition: Design, formalize, and implement quantitative safety and comfort metrics for AV algorithm modules (Perception, Prediction, Motion Planning, and Control). Translate high-level operational design domains (ODDs) and potential failure modes into automatable, objective criteria.

Simulation Test Engineering: Build, execute, and maintain complex open-loop and closed-loop simulation test suites to stress-test software releases, evaluate edge cases, and benchmark module-level and system-level performance.

Failure Triage & Root Cause Analysis: Analyze large-scale simulation outputs to distinguish genuine software regressions from simulation artifact anomalies. Localize root causes to specific modules and deliver actionable diagnostic reports to development teams.

Test Framework Automation: Write production-grade Python scripts and extend core testing frameworks to automate test execution, data ingestion, and statistical reporting.

CI/CD Pipeline Integration: Integrate automated regression suites into continuous integration pipelines (e.g., Jenkins) for seamless, multi-stage testing across daily builds.

Data-Driven Quality Standards: Establish reproducible testing practices, enforcing strict artifact hygiene, dependency management, and quantitative validation over visual inspection.

Autonomous Vehicle Domain Knowledge: Deep understanding of AV stack architecture—including perception, prediction, motion planning, and control—along with their associated failure modes and physical constraints.

Simulation & Test Design: 2+ years of hands-on experience authoring scenarios and executing test cases within Software-in-the-Loop (SIL) or Hardware-in-the-Loop (HIL) simulation platforms.

Quantitative & Safety Metrics Analysis: Demonstrated experience defining and evaluating kinematic and spatial metrics (e.g., Time-to-Collision [TTC], headway, jerk/acceleration profiles, lateral error) using statistical analysis across large datasets.

Python Development: Strong Python scripting skills for data processing, test automation, and test framework creation, with an emphasis on clean code structure and problem-solving.

CI/CD & DevOps Tooling: Practical experience with automated build/test pipelines (e.g., Jenkins, GitHub Actions) and visualization tools (e.g., Grafana, custom dashboards) to report test metrics.

Education: Bachelor’s or Master’s degree in Computer Science, Robotics, Electrical/Software Engineering, Mathematics, Statistics, or a related technical discipline.

Standardized Map & Scenario Formats: Familiarity with lane-level maps (OpenDRIVE, Lanelet2, OSM) or scenario description standards (OpenSCENARIO); hands-on experience with spatial/geometry data pipelines.

Computational Geometry: Foundations in applied geometry, including polyline sampling, curvature evaluation, offsets, and polygon intersection routines.

Industry Simulators: Experience with open-source or commercial simulator tools (e.g., CARLA).

Data Querying & Storage: Proficiency with SQL and relational databases for querying bulk test results.

Safety Regulations & Benchmarks: Exposure to real-world crash databases (e.g., NHTSA CISS/CRSS, FARS) or standard safety testing protocols (e.g., Euro NCAP, ISO 26262/ISO 21448 SOTIF).