Machine Learning Engineer, Agent Simulation

The Agent Simulation group at Zoox is seeking machine learning engineers to enhance agent behaviors, assess performance, and develop tools to prioritize simulation results. You'll work on creating reliable and validated simulations, leveraging real-world driving data and exceptional infrastructure. The role involves researching and implementing state-of-the-art machine learning approaches, finding innovative solutions for agent behaviors, proving ML algorithms outperform heuristics, and building scalable cloud pipelines. You'll analyze differences between simulated and real-world behaviors, and collaborate with safety and autonomy engineers.

Key responsibilities include:

• Implementing and optimizing ML approaches for plausible agent behaviors
• Leveraging large-scale ML infrastructure for new solutions
• Building scalable cloud pipelines for ML solutions in simulation
• Cross-functional collaboration with safety and autonomy teams

Qualifications:

• BS, MS, or PhD in Computer Science or related field
• Experience with training and deploying deep learning models
• Familiarity with production ML pipelines
• Fluency in Python, basic C++ understanding
• Proficiency with Numpy and PyTorch, TensorFlow or JAX
• Strong mathematics skills

Bonus qualifications include experience with LLMs, reinforcement learning, imitation learning, and prior work in agent behaviors, prediction, autonomous vehicles, or robotics.

Zoox offers competitive compensation, including salary, Amazon RSUs, and Zoox Stock Appreciation Rights. The salary range is $141,000 to $234,000, with additional benefits such as paid time off, health insurance, and more.

Zoox values diversity and encourages applicants from all backgrounds to apply, even if they don't meet every listed qualification.