Machine Learning Engineer: Robotics ML Generalist

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 looking for a highly motivated engineer with experience deploying machine learning algorithms to physical systems in the real world. The ideal candidate has hands-on experience in perception (e.g., object detection, semantic segmentation, depth estimation) and/or behavior learning methods (e.g., Vision-Language-Action (VLA) models, diffusion policies). More importantly, you’ve shipped ML models to robots in production environments, and you understand the complexities that come with it.

What you’ll do:

• Develop and optimize real-time ML models for edge deployment on robotic systems
• Work with vendors to label data and build robust data extraction and labeling pipelines
• Design custom metrics to evaluate model performance in the field
• Reduce model latency using tools like ONNX, TensorRT, or similar

What we’re looking for:

• Practical experience applying machine learning with deep learning frameworks, such as PyTorch, to solve real-world problems
• Proficiency in Python and comfort with at least one systems language (e.g., C++, Rust)
• Experience deploying ML models to robotic systems or other physical platforms
• Experience incorporating raw sensor data like camera, lidar, radar, IMUs, etc into deep learning algorithms.
• Bonus: Practical application of incorporating 3D geometry into deep learning models
• Bonus: Published work in conferences such as ICRA, IROS, CoRL, CVPR, ECCV, ICCV, ICML, NeurIPS,

***We’re especially interested in engineers who thrive at the intersection of ML research and real-world robotics applications.