Staff ML Validation Applied Scientist

Job Description

Role 

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. 

About the Organization 

The Autonomous Vehicle (AV) organization is dedicated to advancing the development of autonomous vehicles through cutting-edge simulation technologies and novel iterative development processes. 

The Software Validation team focuses on unlocking software launches and continuous release decisions via simulation-led verification and validation strategies, prototypes, and protocols. Our collaborative environment fosters innovation and excellence, allowing us to push the boundaries of what is possible in autonomous vehicle testing. 

What You’ll Do 

As a Staff ML Validation Research Engineer, you will: 

• 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. 

Your Skills & Abilities 

• 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