Behavior ML Engineer

Join the team bringing advanced autonomy to the built world

At Bedrock, we're moving AI out of the lab and into the real world. Our team includes veterans who helped launch Waymo, scaled Segment to a $3.2B acquisition, and grew Uber Freight to $5B in revenue. Today, we're deploying autonomous systems on heavy construction equipment across the country, improving safety on job sites and accelerating schedules on critical infrastructure projects.

We're not here debating the future of AI. We're deploying it in the real world. In just two years, we've raised $350M and achieved the first fully autonomous excavator deployments in construction.

This is where algorithms meet steel-toed boots. You'll work alongside construction veterans and world-class engineers to solve physical-world problems that simulations can't touch. If you're ready to do meaningful work on hard problems, we'd love to have you join us.

About the Role & Team

Teaching a 40-ton excavator to move like an expert operator is a very different problem from teaching a car to stay in its lane. The motions are multimodal, there are many good ways to swing, dig, and dump and the consequences of getting them wrong are measured in cubic yards and bent steel. Bedrock's Behavior ML team builds the learned policies that decide what our machines actually do, and diffusion policies are a central bet: models that can represent the full distribution of expert behavior instead of averaging it into mush. As our Behavior ML intern, you'll help train those policies and build the evaluation that tells us whether they're genuinely better working alongside two hosts who sit on both the training and evaluation sides of the problem.

What You'll Do

• Train and iterate on diffusion flow matching, and related behavior policies using real fleet demonstration data and simulated rollouts

• Run architecture, conditioning, and hyperparameter explorations, and turn the results into clear findings the team can build on

• Build and improve evaluation pipelines that score behavior models on task success, smoothness, safety margins, and operator-likeness

• Investigate failure modes - distribution shift, mode collapse, out-of-distribution scenes and propose fixes

• Work with the simulation and eval teams to make sure offline metrics actually predict on-machine performance

• Contribute to the shared training codebase with clean, reviewed, reproducible work

• Share results regularly with the behavior, controls, and autonomy teams

What We're Looking For

Required