About the role
The Simulation team builds the virtual world in which the autonomy stack is tested before it touches the road. That means a renderer that produces plausible lidar, radar and camera data, traffic agents that behave like people, and a scenario framework that replays real fleet events and perturbs them into thousands of variations.
A simulator is only useful if its answers can be trusted, so much of the work is closing the gap between synthetic and real: sensor models validated against recorded returns, vehicle dynamics matched to track data and metrics that agree with what happens on the road. Planning, Perception and Safety all rely on your results to decide what ships, and other Clexerl ventures reuse the scenario engine for their own machines.
The team runs large batch workloads on cloud compute and keeps every run reproducible, down to the seed and the software version.
What you’ll do
- Build and extend a closed-loop simulation platform that runs the full autonomy stack against synthetic and replayed scenarios.
- Develop sensor models for lidar, radar and camera, including noise, occlusion, beam divergence and weather effects, and validate them against real recordings.
- Create scenario generation and mutation tools that turn fleet near-misses into parameterised test cases with coverage tracking.
- Model reactive traffic agents, using rule-based, data-driven or learned behaviour, so interactions are realistic rather than scripted.
- Scale simulation across large compute clusters with deterministic replay, result storage and clear pass or fail criteria.
- Quantify the sim-to-real gap and publish it, so teams know which conclusions the simulator can support.
What you’ll bring
- Experience building simulators, game engines, physics engines or large test infrastructure for robotics or autonomous systems.
- Strong software engineering in C++ and Python, with attention to performance, determinism and clean interfaces.
- Knowledge of 3D graphics or ray tracing, rigid-body dynamics and sensor physics sufficient to model returns credibly.
- Experience with distributed batch compute and the discipline of reproducible runs, including seeding and versioning.
- Statistical sense about test coverage: how many scenarios are enough, and what a pass actually proves.
- Willingness to compare the simulator to reality and report plainly where it falls short.
Nice to have
- Experience with neural rendering or generative models to create realistic sensor data from logged drives.
- Familiarity with scenario description languages and standards for scenario-based testing.
- Experience with GPU ray tracing for lidar or radar simulation at scale.
- Background in importance sampling or adaptive stress testing to find rare failures efficiently.
Work you might take on
- 01
Build a lidar model that reproduces return dropout on wet asphalt and dark vehicles, and validate it against fleet recordings.
- 02
Automate conversion of a flagged fleet event into a scenario family with varied speeds, positions and agent behaviours.
- 03
Add adaptive stress testing to search for planner failures in intersection scenarios far faster than random sampling.
- 04
Produce a sim-to-real report comparing braking, steering and perception outputs between simulation and track data for the same manoeuvres.
Compensation
$200K – $330K
The US base salary range for this role. 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.