Want to know if this job is worth applying to?
San Francisco, California, United States
Hybrid
At Bedrock, we’re moving AI out of the lab and into the real world. Our team is composed of industry 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 machinery across the country, accelerating project schedules of billion-dollar infrastructure projects and improving safety on job sites. Backed by $350M in funding, we’re working quickly to close the gap between America's surging demand for housing, data centers, manufacturing hubs, and the construction industry's growing labor shortage.
This is where algorithms meet steel-toed boots. You’ll collaborate with construction veterans and world-class engineers to solve physical-world problems that simulations can’t touch. If you're ready to apply cutting-edge technology to solve meaningful problems alongside a talented team—we'd love to have you join us.
Bedrock is bringing autonomy to the construction industry! We’re a group of veterans from the autonomous vehicle industry who are passionate about bringing the benefits of automation to areas in the construction industry currently underserved by the market.
We're building out our first fleet of retrofitted autonomous construction machines, and we're looking for a Senior Perception Sensor Software Engineer to own sensor validation and data quality for our safety-critical system. You'll ensure that the camera, lidar, and IMU data feeding our perception and behavior models is trustworthy and rigorously characterized. You'll detect when system performance degrades and quantify its impact on our ability to operate safely. You'll shape how we build our sensor data representations, and partner closely with the teams working on object detection, tracking, and behavior planning.
Own the sensor validation framework for our safety-critical system
Develop ML models and novel approaches for sensor data validation and anomaly detection across camera, lidar, IMU, and all other sensors on our robots
Build the data pipelines, ground-truth infrastructure, and evaluation frameworks that quantify sensor data quality and expose corner cases
Partner with the perception and behavior teams so they can deeply understand and trust the data feeding their models
MSc or advanced degree in Computer Science, Robotics, or a related field
4+ years of professional experience shipping deep learning models to production (ideally on robotic or other embedded platforms), with strong hands-on experience in PyTorch or another deep learning framework
Proficient in Python and comfortable reading and writing at least one systems language (e.g. C++, Rust)
Hands-on experience incorporating raw sensor data (camera, lidar, IMU) into deep learning pipelines
Solid grounding in 3D geometry, sensor calibration (intrinsics/extrinsics), coordinate transforms, and camera/image re-projection algorithms
Strong data analysis skills across statistical characterization of sensor data, corner-case and anomaly discovery, and evaluation design
Deep knowledge of sensor physics: noise models, failure modes, how environmental conditions affect lidar and cameras
Prior experience with safety-critical systems
Experience with the Rust programming language
Published work in top-tier venues such as ICRA, IROS, CVPR, ECCV, ICCV, CoRL, or RSS
Based in the Bay Area with the ability to be onsite at our testing facility and SF office 3-4 days a week
Our roles are often flexible. If you don't fit all the criteria, or are in another location (especially one where we have an office like SF or NY) please apply anyway! We'd love to consider you.
