Staff Software Engineer - Autonomy Evaluation joins the Evaluation team to build and evolve the ecosystem powering autonomous driving technology. This role involves developing metrics, automated workflows, and analysis approaches to enable data-driven decisions across development and verification. You will define strategies for evaluating performance across the autonomy stack, lead cross-functional efforts with systems and simulation teams, and invent statistical and machine learning methods to detect regressions and quantify behavior at scale. The position requires expertise in Python, C++, SQL, and tools like Pandas, NumPy, SciPy, and PyTorch. Candidates must possess experience in robotics or autonomous systems, specifically involving perception, planning, and control. You will solve complex problems regarding risk assessment, release gating, and the creation of unified analytics frameworks to ensure safety and quality for advanced driver assistance systems.
What does a Software Engineer earn in California?
Median $214000 from 775 postings across 63 companies.
Define the strategy and architecture for metrics and analyses to evaluate autonomous driving software performance across the autonomy stack.
Lead cross-functional efforts with engineering and data teams to integrate evaluation into development workflows and release decisions.
Develop new statistical and machine learning methods to quantify performance, detect regressions, and identify system behavior patterns at scale.
Own and refine key AV evaluation metrics and KPIs used for critical readiness and safety decisions.
Synthesize results and trade-offs to provide actionable feedback to stakeholders through interactive dashboards.
Root-cause discrepancies in anomalous data to ensure the reliability of autonomous systems.
Manage large-scale test scenario libraries, continuous evaluation pipelines, and risk assessment components.
What we're looking for
7+ years of experience with robotics or autonomous systems software across perception, planning, and control subsystems.
3+ years of experience leading evaluation of complex dynamic systems using numerical and ML approaches on large-scale time series data.
Proficiency in developing Python within production team environments.
Strong ability to work within large C++ autonomy codebases.
Proven cross-team technical leadership including defining strategies and influencing system and architecture decisions.
Ability to systematically root-cause discrepancies and investigate anomalous data.
Bachelor’s, Master’s, or PhD degree in Computer Science, Robotics, Mechanical Engineering, Aerospace Engineering, Machine Learning, or a related field.