Principal Software Engineer, Autonomy Evaluation
zoox
Job Summary
Zoox is seeking a Principal Software Engineer to lead AI evaluation for autonomous driving. The role involves defining and planning advanced AI evaluation beyond safety, progress, and comfort. Responsibilities include prototyping concepts with autonomy leaders, improving data curation and metrics development, and collaborating with foundation model teams to leverage models for offline validation. The engineer will also work with infrastructure and simulation teams to build new AI evaluation capabilities and provide technical mentorship. This position requires a strong understanding of machine learning evaluation in autonomous driving, GenAI, or robotics, with a proven track record of technical leadership in large-scale AI organizations. Experience with production machine learning pipelines, C++ or Python, and strong mathematics skills are essential.
Must Have
- Lead AI evaluation beyond safety, progress, comfort
- Prototype and evaluate concepts
- Drive process improvements
- Collaborate with foundation model teams
- Develop models to improve validation speed and quality
- Build new AI evaluation capabilities
- Provide technical mentorship
- BS, MS, or PhD in computer science or related field
- Experience with ML evaluation in Autonomous Driving, GenAI, or Robotics
- Technical leadership in large-scale AI organizations
- Experience with production ML pipelines
- Fluency in C++ or Python
- Strong mathematics skills
- 10+ years of experience
Good to Have
- Experience using foundation models for ML evaluations
- Experience training and deploying Deep Learning models
- Direct experience in Autonomous Driving
Perks & Benefits
- Paid time off (sick leave, vacation, bereavement)
- Unpaid time off
- Zoox Stock Appreciation Rights
- Amazon RSUs
- Health insurance
- Long-term care insurance
- Long-term and short-term disability insurance
- Life insurance
Job Description
In this role, you will
- Technically lead the definition and work planning in advancing AI evaluation beyond safety, progress and comfort.
- Collaborate with autonomy software leaders, data scientists and engineers to prototype and evaluate the concepts.
- Drive process improvements on data curation, metrics development and metrics quality.
- Collaborate with Zoox Foundation Model team to leverage the foundation models used for offline validation and/or triage.
- Use multi-modal data from across the company to develop models and strategies that improve the speed and quality of our validation process.
- Work with Infrastructure and Simulation teams to build new capabilities in AI evaluation that are not currently available.
- Provide technical mentorship to the broader groups at Zoox.
Qualifications
- BS, MS, or PhD degree in computer science or related field
- Experience with ML evaluation in Autonomous Driving, GenAI, or Physical AI, Robotics etc.
- Proven track record of technical leadership in large-scale AI organizations
- Experience with production Machine Learning pipelines: dataset creation, training frameworks, metrics pipelines
- Fluency in C++ or Python
- Strong mathematics skills
- 10+ years of experience
Bonus Qualifications
- Prior experience with using foundation models to advance ML evaluations
- Experience with training and deploying Deep Learning models
- Direct working experience in Autonomous Driving