Senior Camera Pipeline and Image Quality Engineer

About the company

Bedrock Robotics develops autonomous construction technology that retrofits heavy equipment to operate as coordinated, driver-less fleets.

About this role

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 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. We are 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. Cameras power our autonomy stack on rugged construction machines across all lighting conditions, from full sun to complete darkness, in scenes with high dynamic range, dust, glare, and unpredictable site lighting. We are looking for a senior camera pipeline and image quality engineer to own the full camera pipeline: from embedded drivers and data interfaces through ISP tuning, ensuring our cameras deliver usable imagery for both ML perception models and human teleoperation across a wide range of lighting conditions. Key Qualifications - Hands-on experience tuning ISP pipelines on real hardware (auto exposure, auto white balance, tone mapping, demosaicing, noise reduction, and HDR fusion) with a track record of diagnosing and correcting failure modes such as AE anchoring on bright point sources, aggressive HDR sub-frame ratio compression, and tone mapping that crushes scene content in mixed-light environments - Deep familiarity with AE algorithm internals: histogram weighting, metering zone selection, exposure ratio control in multi-exposure HDR pipelines, and lux estimation, and how these interact with scenes containing simultaneously very bright and very dark content - Hands-on experience writing or integrating embedded camera drivers (V4L2, MIPI CSI-2, GMSL, I2C) and building the tooling and software interfaces that expose ISP and imager control to an autonomy software stack - Familiarity with camera data pipelines on embedded platforms: frame synchronization, timestamping, compression, bandwidth management, and integration with autonomy middleware (ROS2 or similar) - Understanding of how ISP tuning choices affect downstream ML/perception model performance, and experience validating that pipeline changes do not degrade existing model behavior - Working knowledge of camera sensor fundamentals (CMOS architecture, shutter types, CFA patterns, dynamic range, sensitivity, and binning) sufficient to reason about how sensor choice and configuration interact with ISP behavior - Working knowledge of radiometry sufficient to interpret photon budget models, SNR predictions, and motion-blur constraints as inputs to ISP tuning requirements - Strong data analysis skills, including experience working with large datasets, building quantitative models, and using statistical methods to characterize real-world system behavior - 8+ years of relevant industry experience in ISP tuning, embedded camera systems, image quality engineering, or closely related roles Responsibilities - Own the camera pipeline end to end: diagnose image quality failures, tune ISP parameters, and validate improvements across the full operating radiometric range from bright daylight to night with machine-mounted illumination - Own embedded camera driver development and integration: register-level control, frame synchronization, and software interfaces that expose runtime ISP parameter control to the autonomy stack - Characterize existing ISP pipeline behavior from first principles: identify root causes of image quality failures using parameter-level access, histogram analysis, raw vs processed frame comparison, and controlled test scenes - Tune ISP and imager settings (exposure, white balance, HDR sub-frame ratios, tone mapping, noise reduction) to optimize image quality for both ML perception models and remote assistance/teleoperation - Establish and run test protocols that confirm ISP changes improve low-light performance without adversely affecting existing daytime model performance or training data compatibility - Work closely with perception, autonomy, and sensing engineering to translate scene and platform constraints (yaw rates, lux levels, detection ranges) into concrete ISP tuning targets - Debug camera issues from sensor/ISP register state through to captured imagery, both in the lab and in the field - Define and drive image quality characterization methodologies (SFR/MTF, noise, dynamic range, photon transfer curves) and track performance across hardware and ISP firmware generations - Manage relationships with ISP, camera module, and embedded compute vendors Education and Experience - Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, Optical Engineering, Physics, or a related field - 8+ years of experience in embedded camera systems, ISP tuning, image quality engineering, or closely related roles with a strong pipeline focus - Demonstrated ability to characterize, diagnose, and improve camera image quality on fielded hardware - Embedded systems experience: comfort at the hardware/software boundary, driver-level debugging, and working with real-time constraints on embedded compute platforms - Comfortable working in C/C++ and/or Python for driver-level work,