2027 Internship Behavior ML Engineer, Learned Manipulation Policies
Bedrock Robotics · San Francisco, CA
About this role
## Bedrock — Behavior ML Engineer Intern (2027) ### About the role At Bedrock, we’re moving AI out of the lab and into the real world—deploying autonomous systems on heavy construction equipment across the country to improve safety and accelerate critical infrastructure schedules. As a **Behavior ML Intern**, you’ll help train and evaluate **learned behavior policies** (with diffusion policies as a central bet) that decide what our machines actually do—aiming to represent the full distribution of expert behavior rather than averaging it into something less useful. ### 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 results into clear findings - Build and improve **evaluation pipelines** to score behavior models on: - task success - smoothness - safety margins - operator-likeness - Investigate failure modes (e.g., **distribution shift**, **mode collapse**, **out-of-distribution scenes**) and propose fixes - Partner with simulation and evaluation teams to ensure **offline metrics 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** - Currently pursuing a **BS, MS, or PhD** in computer science, robotics, machine learning, or a related field (or equivalent research/industry experience) - Strong **Python** and hands-on experience training models in **PyTorch** (or equivalent) - Working understanding of **generative modeling** (diffusion models, flow matching, VAEs, etc.) and **imitation learning / behavior cloning** - Experience running and interpreting real training experiments (ability to distinguish improvement from noise) - Clear communication: explain what you tried, what happened, and what you’d do next **Preferred** - Published work or substantial project experience in diffusion, flow matching, robot learning, or imitation learning - Experience training **Vision Language Action (VLA)** models - Experience training **Reinforcement Learning (RL)** policies for robot manipulation - Experience evaluating policies in simulation and reasoning about the **sim-to-real gap** - Familiarity with large-scale training infrastructure and experiment tracking tooling - Exposure to robotics, autonomous vehicles, or other physical-world control problems - Interest in construction, earthwork, or heavy equipment - *No prior experience required* ### Equal Opportunity Bedrock Robotics is an **Equal Opportunity Employer** and is committed to building a diverse and inclusive workplace. ### Accommodations If you need an accommodation during the application or interview process, let your recruiter know so we can support you.
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.