2027 Internship State Estimation, Learned Mapping & Semantic SLAM
Bedrock Robotics · San Francisco, CA
About this role
## 2027 Internship — State Estimation, Learned Mapping & Semantic SLAM **About Bedrock** 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 deploy autonomous systems on heavy construction equipment across the country—improving safety on job sites and accelerating schedules on critical infrastructure projects. **About the Role & Team** Construction sites change with every bucket of dirt. Our **State Estimation** team builds the maps and localization systems that help autonomous excavators understand where they are and how the terrain is changing. As an intern, you’ll explore how modern learning-based methods can improve our **geometry-first mapping stack**—for example: - Localizing reliably in terrain that looks the same in every direction - Building maps that hold up through dust and occlusion - Labeling maps semantically so the machine can distinguish materials to dig (e.g., haul roads, spoil piles, berms) You’ll test ideas on real fleet data, compare against strong classical baselines, and deliver a prototype the team can build on. --- ## What You’ll Do - Prototype learned SLAM and mapping methods (e.g., place recognition, odometry, depth completion, neural occupancy/surface representations) - Fuse lidar and camera segmentation into consistent **3D semantic maps** (potentially using vision foundation models or open-vocabulary segmentation) - Develop methods for changing terrain, moving material, sparse returns, dust, occlusion, and perceptual aliasing - Train models on fleet lidar/camera data and build evaluation pipelines vs. existing methods and ground truth - Partner with perception and planning teams to identify which map properties matter most downstream - Deliver a documented prototype, experimental results, and recommendations for future work --- ## What We’re Looking For **Required** - Pursuing a **BS, MS, or PhD** in CS, robotics, electrical engineering, or related field (or equivalent research/industry experience) - Strong **Python** skills and hands-on model training experience with **PyTorch** (or similar) - Solid understanding of **3D geometry**, coordinate frames, and transforms - Familiarity with **SLAM and mapping fundamentals**, point clouds, or depth data - Comfort working with messy sensor data and designing experiments that distinguish real improvements from noise **Preferred** - Experience with learned SLAM, semantic mapping, or 3D scene understanding - Experience with neural scene representations (e.g., NeRFs, 3D Gaussian splatting, neural occupancy, signed distance fields) - Experience applying vision foundation models (e.g., DINOv2, SAM) to 3D/robotics problems - Experience with lidar processing or multi-sensor fusion - Exposure to autonomous vehicle, off-road, or field robotics data - Familiarity with **Rust or C++**, and **ROS** (or similar robotics middleware) --- ## Equal Opportunity Employer Bedrock Robotics is an Equal Opportunity Employer. We’re committed to building a diverse and inclusive workplace. ## Reasonable Accommodations If you need an accommodation to participate in the application or interview process, please 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.