About the role
As an intern you join a real perception or planning team for a summer and own a defined problem from first week to a result that runs on the vehicle. Past projects have included improving a tracker on a particular failure, adding an evaluation metric and building a data-mining query for rare scenes.
You are paired with a mentor on the team and given a scoped goal, a dataset and access to the same tools as full-time engineers: fleet logs, replay, simulation and the code review process. Work is judged the way everyone's is, by whether it holds up on real data. Interns also see how Perception connects to Planning, Safety and the Frontier AI research that informs our models.
You write and present your work at the end of the summer to the wider team, including what did not work.
What you’ll do
- Work on a scoped perception, localisation or planning problem with a named mentor and a clear definition of success.
- Write production-quality C++ or Python, submit it for code review and respond to feedback within the team's normal process.
- Analyse fleet logs and replay results to understand a failure mode, and propose and test a fix.
- Run experiments, record results and keep notes so another engineer can reproduce your work after you leave.
- Attend team reviews and ask questions, and spend time on the track or with the field team to see how the system behaves on the road.
- Present your project, results and limitations to the autonomy group at the end of the programme.
What you’ll bring
- Current enrolment in a degree programme in robotics, computer science, electrical or mechanical engineering, mathematics, physics or a related field.
- Solid programming ability in Python or C++, shown through coursework, projects, competitions or open-source contributions.
- Coursework or project experience in at least one of computer vision, linear algebra and probability, control, or machine learning.
- Curiosity about how real systems fail, and willingness to dig into data rather than guess.
- Clear written and spoken communication, and comfort saying what you do not yet understand.
- Ability to work on site in Columbia, Maryland for the full programme.
Nice to have
- Experience with a robotics competition, student autonomous vehicle team or research lab project involving real sensors.
- Familiarity with ROS, PyTorch or point cloud libraries such as Open3D or PCL.
- Prior exposure to Kalman filtering, SLAM or trajectory optimisation in coursework or personal projects.
- Contributions to open-source robotics or computer vision code.
Work you might take on
- 01
Add a new evaluation slice to the tracking regression suite that measures identity switches for pedestrians near parked vehicles.
- 02
Prototype a query over fleet embeddings that retrieves scenes with unusual road debris and review how often the results are useful.
- 03
Compare two lidar-to-map registration settings on logged drives and recommend a configuration backed by error plots.
- 04
Implement a comfort metric for planned trajectories, such as jerk and lateral acceleration, and report it across a library of simulated scenarios.
Compensation
$55K – $60K
The US base salary range for this role, annualised. Every offer also includes equity in Clexerl and, when it spins out, in the venture you help build. We tell you the reasoning behind your number.
Benefits
Health, fully covered
Medical, dental and vision for you and your dependants, premiums paid in full.
Two kinds of equity
Equity in Clexerl, plus a stake in the venture you help build when it spins out.
22 weeks parental leave
Fully paid, for every parent, however your family arrives.
Rest that sticks
Flexible time off with a four-week minimum we actually check on, plus a company-wide week in December.
Learning and compute
A yearly budget for courses, conferences and books, and compute credits for side projects.
401(k) with a 4% match
Matched from your first paycheque and vested immediately.
How we hire
Apply 5 minutes
Send links to what you have built and a few lines on why this role. No cover letter needed.
Intro call 30 minutes
A conversation with the hiring manager about the work, the team and what you want next.
Work sample 2–4 hours
A paid take-home or a pairing session on a real-shaped problem. You pick the format.
Studio day One day
Meet the team, go deep on your work and ours. Remote or in person.
Offer Within 5 days
A written offer with the full range, the equity and the reasoning behind both.
Opens an email with a short template. Links beat résumés.