Technical Lead - Autonomy Evaluation
About this role
Developing the log replay, scoring, and evaluation platform for autonomous vehicles occupies the core of daily operations in this role. Engineers in this position own the metrics that determine release readiness, managing everything from recorded logs to scored regression suites and final deployment reports across on-road fleets.
Atoms builds Physical AI systems to automate complex real-world industries like food, mining, and transport, bringing intelligence to physical infrastructure. This role exists to establish rigorous, scalable evaluation standards that ensure software safety and reliability before vehicles reach the road. Candidates who thrive here are methodical technical leaders with deep experience in autonomous systems validation, large-scale data pipelines, and cross-functional mentorship.
What you will do
- Define and oversee safety, behavior, and release criteria metrics including collision avoidance, trajectory agreement, and passenger comfort.
- Manage the end-to-end log replay pipeline to evaluate perception, localization, and planning algorithms against ground truth data.
- Build and maintain regression and benchmarking systems to assess new software versions against historical data across the entire corpus.
- Develop data mining strategies to uncover rare and important edge cases for targeted test coverage and scenario generation.
- Ensure deterministic and reproducible execution of evaluation suites while tracking and optimizing compute costs per replay-hour.
- Establish engineering standards for metric definitions, test design, code review, and evaluation result reporting.
- Mentor team members, set the technical bar for the evaluation function, and actively participate in the hiring process.
What you need
- Hold a Bachelor's degree in Computer Science, Robotics, Electrical Engineering, Statistics, or a related field with at least eight years of relevant experience.
- Bring a minimum of two years of experience functioning as a technical lead or engineering manager for an evaluation, validation, or test team.
- Demonstrate prior ownership of an offline or system-level evaluation system for autonomous vehicles, robotics, or large-scale machine learning models in production.
- Possess hands-on experience building large-scale log replay systems with open-loop and closed-loop evaluation against ground truth.
- Show proficiency in Python alongside the capability to read, navigate, and debug existing C++ codebases.
- Display a working understanding of end-to-end autonomous systems encompassing sensing, perception, localization, planning, and controls.
Benefits
- Medical, Dental, Vision, Disability, and Life Insurance
- Flexible Spending Account / Health Savings Account Options
- 401(k) and Equity
- Sick Time, Unlimited Flexible Time Off, and Paid Holidays
- Paid Parental Leave and Pre-Tax Commuter Benefit Plan
- Team lunch in the SoMa office every Tuesday and Thursday
Skills and tech stack
Questions candidates ask
What is the remote work policy for this position?
This role is based in the San Francisco office location. All office-based teams work onsite, five days a week.
What is the salary range for this role?
The base salary range for this role is $185,000 to $242,000 per year, with actual compensation determined on an individual basis depending on experience, skills, and qualifications.
What kind of technical background is required?
Candidates need a background in robotics or autonomous systems, proficiency in Python, the ability to debug C++ codebases, and experience running evaluation pipelines on GPU clusters or large-scale compute.
What additional rewards are included besides base salary?
Employees may be eligible for equity awards alongside a benefits package that includes medical, dental, vision insurance, a 401(k), unlimited flexible time off, and commuter benefits.
The application is on the official ATOMS Careers page careers page.
Apply on company site