The Multiverse team at Waymo is responsible for the end-to-end evaluation of our autonomous driving software. We don't just look at what happened; we look at what could have happened. Using a mix of real-world testing and counterfactual simulation, we stress-test the Waymo Driver’s safety and reliability before it ever hits the road. Join us in the Driver Understanding and Evaluation (DUE) group to develop the rich metrics that define the future of autonomous mobility.

You will:

• Build the infrastructure to administer a “virtual driver’s test” for the Waymo Driver. Design, implement, and operate scalable simulation data pipelines and/or real world monitoring in order to evaluate the driving capability of the Waymo Driver, and at low latency in the real world.
• Improve the signal quality provided by the “virtual driver’s test” and measured in the real world. Measure and improve the quality of individual simulations as well as that of the overarching simulation workflows. Seek to answer whether the results of the “virtual driver’s test” are predictive of the Waymo Driver’s real-world driving behavior. 
• Apply ML models from partner teams, and optionally contribute to them yourself, to improve the efficiency of our “virtual driver’s test”: simulate the most interesting situations and report the most interesting simulation results.
• Apply software engineering best practices in order to improve code health and developer experience in the “virtual driver’s test” and the real world monitoring development ecosystems.
• Partner with cross-functional teams including Data Science and Systems Engineering who will help with number crunching and expert understanding of the Waymo Driver internals.

You have:

• 3+ years of full-time software engineering experience, or a quantitative PhD with software engineering experience
  • C++ proficiency
  • Python familiarity 
  • SQL familiarity 
• Strong verbal and written communication skills
• Excited about autonomous driving, Sim+Eval, eager to learn

We prefer:

• Industry or doctoral experience in a quantitative- or quality- focused engineering role in which you were performing tasks like developing hypotheses, designing and running experiments, processing data from experiments, synthesizing conclusions, and ensuring the long term stability and health of the production system.
• B.Sc. in Computer Science
• Experience working with large FAANG scale distributed systems.