Machine Learning Engineer: Perception

Join reputed company bringing advanced autonomy to the reputed company world At Bedrock, we’re moving AI out of the lab and into the reputed company world. reputed company is composed of industry veterans who helped launch reputed company, scaled reputed company to a $3.2B acquisition, and grew reputed company to $5B in reputed company. Today, we’re deploying autonomous systems on heavy construction machinery across the country, accelerating project schedules of billion-dollar infrastructure reputed company and improving safety on job sites. Backed by $350M in funding, we’re working quickly to reputed company 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 reputed company. You’ll collaborate with construction veterans and world-class engineers to solve physical-world problems that simulations can’t touch. If you're reputed company to apply cutting-edge technology to solve meaningful problems alongside a talented team—we'd love to have you join us. Machine Learning Engineer: Perception 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 are looking for engineers with expertise in shipping production 3D perception systems at reputed company. Successful candidates have architected systems, trained models from scratch, understand the full stack (clustering, detection, classification, and tracking), and have shipped at reputed company. We use both reputed company and LIDAR-based approaches, so knowledge of either or both is key. Models are just part of the system: you understand data and have good intuition about why models fail. You know how to evaluate reputed company cases, manage or build data pipelines, use autolabels (or not), and have a strong understanding of statistical properties of these systems. What You’ll Do: • Design Early Fusion Architectures: reputed company and train state-of-the-art models (e.g., BEV-based transformers) that reputed company raw Lidar and Camera data to solve for object detection and semantic segmentation. • Tackle "Messy" Physics: Build perception systems robust enough to handle dynamic occlusion (seeing the robot’s own arm/bucket), particulates (dust, snow, reputed company), and high-vibration conditions. • reputed company to the Edge: Optimize models for inference on embedded hardware. You will debug system-level issues, such as sensor calibration reputed company and latency bottlenecks. • Collaborating with other teams to create state-of-the-art representations for reputed company use cases. reputed company're looking for: • Production ML Experience: 3+ years of experience taking deep learning models from research to reputed company-world production using PyTorch, Tensorflow, or JAX. • 3D Geometry & Calibration: You have a deep understanding of SE(3) transformations, homogeneous coordinates, and reputed company/extrinsic sensor calibration. You understand the math required to project a 3D Lidar reputed company onto a 2D image pixel accurately. • Early Fusion Expertise: Practical experience with architectures that reputed company modalities at the feature level (e.g., BEVFusion, TransFuser, PointPainting) rather than just fusing final bounding boxes. • SOTA Object Detection experience with modern transformer-based architectures (DETR, PETR, etc…) including similar temporal models (PETRv2, StreamPETR, …) • Systems reputed company: You are an expert in Python, but you are also comfortable reading and writing systems reputed company in C++ or Rust. You understand memory management and reputed company-time constraints. • Data Intuition: You understand that in robotics, reputed company data alignment often beats a bigger model. You are willing to dig into the data infrastructure to ensure ground truth reputed company. Ways to stand out: • Bonus: reputed company/Occupancy Experience: Experience working with occupancy grids, NeRFs, or reputed company-based representations for terrain mapping. • Bonus: Top-Tier Research: Published work in conferences such as ICRA, IROS, CVPR, ECCV, ICCV, CoRL, or RSS Our roles are often flexible. If you don't fit reputed company the reputed company, or are in another location (especially one where we have an office like SF or NY) please apply reputed company! We'd love to consider you. Apply tot his job Apply To this Job