This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
As a Staff ML Validation Applied Scientist on the Software Validation team within the Autonomous Vehicle (AV) organization, you will lead applied machine learning research focused on improving verification and validation of ML components and autonomous driving behavior at scale. You will push the frontier of simulation-led ML validation, creating metrics, tools, and agentic workflows that make it dramatically faster, more automated, and more robust to evaluate autonomy systems across large fleets, diverse scenarios, and continuous release cycles. You will transform advanced ML research into working prototypes and production-grade validation services, including AI validation critics that automatically review model behavior, logs, and simulation traces to surface issues, regressions, and coverage gaps.
Job Responsibility:
Lead ML-centric validation strategy for deep learning components across perception, prediction, and planning in AV, defining evaluation methodologies with cross-functional partners
Build AI validation critics and agentic acceleration workflows using LLM- and model-based agents plus orchestration to automate scenario review, anomaly detection, and end-to-end validation flows
Prototype ML research into scalable tools by transforming ML research into performant tools integrated into CI/CD and large-scale pipelines, owning key behavior and ML validation services and data pipelines
Drive simulation-based ML evaluation at scale by evaluating deep learning modules in realistic sensor and traffic simulation and expanding behavioral and scenario coverage tightly linked to ML models
Provide cross-functional collaboration and leadership across Simulation, Safety, Systems Engineering, Autonomy, and tools teams through reviews, roadmapping, standards, and mentorship focused on high-quality, automation-first software
Requirements:
8+ years of experience and MS/PhD in Computer Science, Machine Learning, Robotics, Software Engineering, Data Science, or a related field
Strong proficiency in Python and at least one systems language (e.g., C++), with experience building production systems over large datasets
Deep understanding of and experience evaluating modern ML for robotic systems
Hands-on experience using AI agents, LLM-based tools, or workflow orchestration to automate parts of the development, validation, or operations lifecycle
Demonstrated ability to design and implement behavioral and ML metrics and associated tooling for validation and regression detection of complex ML systems
Strong analytical skills and systems thinking
able to reason about complex AV behavior and ML model interactions and turn insights into code and tools
Effective communicator who can work across teams and provide technical leadership and mentorship to other engineers and researchers
Nice to have:
Background in autonomous vehicles, vehicle development, or ADAS
Demonstrated impact from introducing automation and AI-assisted tooling (e.g., AI agents, AI validation critics, smart monitoring) that improved scale, reliability, or engineering velocity in ML validation workflows
Experience building verification and validation tools or infrastructure for safety-critical ML or control systems
Experience working with simulation environments and large scenario or telemetry datasets for ML evaluation and behavior validation