Internship 2027 Behavior Machine Learning Engineer, World Models
Bedrock Robotics Inc18 hours ago
Responsibilities
- Train and evaluate world models on real fleet data collected from autonomous machines.
- Run architecture explorations and ablations and assess which approaches produce genuine improvements.
- Build evaluation harnesses and metrics for measuring model quality.
- Collaborate with behavior and controls teams to connect model outputs to planning and control.
- Present findings and create a foundation for continued team development.
Requirements
- Currently pursuing a BS, MS, or PhD in computer science, machine learning, robotics, or a related field, or bringing equivalent research or industry experience.
- Strong Python skills and hands-on experience training models in PyTorch or an equivalent framework.
- Ability to read research papers and implement their methods.
- Comfort working with messy, real-world data rather than only curated benchmarks.
- Sound experimental judgment and ability to distinguish real results from noise.
- Preferred: experience with world models, video prediction, or sequence modeling, including systems such as DreamerV3, V-JEPA 2, Genie 3, GAIA-2, or NVIDIA Cosmos.
- Preferred: background in reinforcement learning or imitation learning.
- Preferred: prior work with robotics or autonomous vehicle data.
- Preferred: familiarity with large-scale training infrastructure.
Categories
ML EngineeringRobotics
About Bedrock Robotics Inc
Bedrock Robotics builds autonomous control systems that retrofit heavy construction equipment, enabling driverless operation on large infrastructure and industrial projects. The San Francisco–based, privately held company, founded in 2024, deploys its technology with contractors and project owners to speed schedules and improve job-site safety. Its business centers on upgrading existing fleets and operating them in the field, with software, sensors, and integration services tailored to construction workflows.