Principal Software Engineer - Autonomy Behavior Validation

Principal Software Engineer - Autonomy Behavior Validation The Role As a Principal Software Engineer in the Autonomy Behavior Validation team, you will set the technical direction for turning safety and behavior requirements into a production-grade counterfactual simulation product. You will build a capability that turns real incidents and simulation scenarios into trustworthy engineering evidence for developers, release decisions, and launch decisions. This includes scene reconstruction, implementation of safety-defined attentive-human benchmarks, human and other road-user response models, counterfactual simulation following intervention, controlled scene variation, outcome and severity estimation, and the validation needed to understand when a result is credible enough to support a decision. You will partner with Safety and other stakeholders to define and refine requirements and benchmark definitions, then turn them into scalable, auditable, and repeatable simulation workflows. What You’ll Do Set the technical strategy and architecture for counterfactual behavior evaluation, including operationalizing safety-defined attentive-human benchmarks, counterfactual simulation following human intervention, alternate-policy comparisons, and controlled scene perturbations. Lead the conversion of real incidents and simulation events into executable, provenance-preserving scenarios with enough fidelity, repeatability, and uncertainty characterization to support engineering and safety decisions. Implement and validate human and other road-user response models against agreed benchmarks and requirements, including perception and reaction timing, maneuver selection, vehicle dynamics, and the range of plausible outcomes. Define and deploy scalable pipelines for parameter extraction, scene reconstruction, counterfactual swaps, fuzzing, simulation execution, outcome estimation, and analysis of large scenario sets. Establish how the counterfactual product and its outputs are validated, including comparison to baseline runs, replay and closed-course evidence, model limitations, confidence, traceability to requirements, and appropriate use of results. Lead work across Behavior, Simulation, Safety, Human Factors, Legal, Product, and Operations, turning complex results into clear engineering actions, safety-case evidence, and release recommendations.

Master’s degree in systems engineering, mechanical engineering, aerospace engineering, electrical engineering, computer science, robotics, human factors, or a related field. 10 or more years of professional experience in autonomous vehicles, robotics, vehicle development, simulation, systems engineering, human factors, or safety-critical validation. A proven record of evaluating autonomous vehicles for a commercial fleet, launch, supervised release, or other high-consequence product decision. Strong understanding of human behavior modeling, driver response, perception and reaction time, vehicle dynamics, uncertainty, and the limits of model-based conclusions. Deep experience building or leading counterfactual, replay, crash reconstruction, incident analysis, or comparable simulation-based evaluation capabilities. Professional experience with simulation evaluation at scale, including scenario generation, parameter sweeps, distributed execution, reproducibility, data quality, and the trade-offs between fidelity, confidence, runtime, and cost. Strong Python and agentic workflow experience. You should be comfortable designing and reviewing production-quality analysis, simulation, and validation software and using code to investigate an engineering question quickly. Strong written and verbal communication skills, with the ability to explain technical results, assumptions, and limitations to both engineering and non-engineering stakeholders. Demonstrated technical leadership across organizational boundaries and evidence of setting direction beyond a single