Research Enginer, Evals

Mostly working with Agentic AI systems, but also large multimodal foundational models.

Develop and maintain software tools for evaluating autonomous vehicle performance.

Contribute to the design and implementation of ML tooling and infrastructure that enhances the overall ML development process.

Design and implement automated ML pipelines to streamline model training, evaluation, and deployment.

Monitor and optimize ML pipelines to improve efficiency, reduce cost and latency, and ensure data quality.

Write and maintain clear and concise documentation for ML models, pipelines, and tools.

Stay up-to-date with ML advancements and identify opportunities for improvement and innovation.

Improve behavior of Autonomous driver in a wide variety of interactive behaviors, leveraging techniques in Optimization and ML.

• Investigate behavioral issues, generate solution categories, and execute on implementation of launches.

• Collaborate with ML / Infra / Product teams to prioritize solutions that align with time sensitive needs while balancing strategic agenda.

• Design solutions that span multiple components in technical stack, influencing solutions developed by dozens of engineers.

• Full stack solution development: including eval, algorithms, modeling and deployment optimization.

• Relevant skills: optimization algorithms (iLQR), autonomous vehicle quality and safety debugging, evaluation methodology, machine learning, developer interfaces, C++ and Python.