Machine Learning Engineer, Simulation Scenario Generation

Do you enjoy applying machine learning to complex, real-world problems in autonomous vehicle testing? The Simulation Scenario Authoring team owns the formats and tools used to create synthetic simulation scenarios. We are looking for a hands-on ML Engineer to integrate, implement, and optimize our next-generation AV scenario generation workflow. This ranges from extending our AI assistant to advancing toward full scenario creation automation from natural language test specification. This role offers a unique chance to deliver immediate user impact while contributing to long-term AI-driven safety validation.

In This Role, You Will:

• Integrate and validate LLMs/VLMs and implement other models for complex scenario generation workflows, leveraging techniques like advanced prompting, agentic tool use, and more. 
• Contribute to tooling for AI-based scenario understanding and validation.
• Collect data and design metrics to drive business intelligence, product iteration, and model fine-tuning.
• Collaborate directly with internal customers and partner teams to provide generative AI solutions for their test creation workflows.
• Directly contribute to the safety and reliability of Zoox's autonomous software.

Qualifications

• MS or PhD in Computer Science, Machine Learning, or related field
• 2+ years of industry experience in Machine Learning
• Solid understanding of LLM or NLP concepts
• Proficiency in Python and ML libraries (PyTorch, NumPy) demonstrated through professional or research projects

Bonus Qualifications

• Practical experience in dataset creation for fine-tuning, system integration of ML models into production, or optimization techniques for low-latency inference systems
• Familiarity with autonomous vehicles, robotics, and/or complex simulation environments
• Hands-on experience in areas like program synthesis, diffusion models, and/or formal methods/V&V
• Relevant publications in conferences (e.g., CVPR, ICCV, RSS, and/or ICRA)