Senior Software Engineer (Statistical Evaluation and Sampling)

Join Waymo, a leader in autonomous driving technology. As a Senior Software Engineer in the Release Evaluation organization, you will develop importance sampling techniques to enhance the efficiency of our evaluation pipelines. You will collaborate with engineers, data scientists, and statisticians to deliver evaluation products and make data-driven decisions. Enjoy a comprehensive benefits package, including medical, dental, and vision insurance, competitive compensation, and a hybrid work model.

• Développer des techniques d'échantillonnage d'importance qui permettent à nos pipelines d'évaluation de fournir de meilleurs signaux avec moins de ressources.
• Trouver des signaux dans nos journaux et simulations qui pourraient nous aider à découvrir plus efficacement des événements rares et importants.
• Construire des systèmes qui optimisent systématiquement plusieurs objectifs dans le cadre de contraintes de ressources.
• 5+ years of experience with
• Strong self-motivation to navigate complex systems and pursue open-ended problems to completion
• Fluency with probability and statistics
• Navigating and modifying a large code base containing a variety of languages, such as C++, Python and SQL
• Experience developing and evaluating sampling methods
• Experience working in the AV industry
• Experience designing, training, evaluating, and applying ML models
• Building data processing pipelines
• PhD in a quantitative field
• Performing statistical analyses
• Experience programming in C++
• Writing, reviewing, and merging code following industry standards for code health and maintainability
• BS in Computer Science, Robotics, Statistics, Physics, Math or another quantitative area
• 7+ years of industry experience (or 3+ years post-doc experience) in a quantitative engineering role
• This includes a proven track record as a technical lead navigating complex, multi-language codebases (C++, Python, SQL) to drive the end-to-end experimental lifecycle: developing hypotheses, designing and executing large-scale experiments, and building robust data pipelines