Bedrock Robotics
Machine Learning Engineer: Imitation and Reinforcement Learning for Robotics
Bedrock Robotics, San Francisco, California, United States
Overview
Machine Learning Engineer with a focus on behavior learning, data-driven behavior policies, and robust data infrastructure. Develop and scale state-of-the-art learning architectures and build data systems that enable reliable, scalable, and reproducible production models. Responsibilities
Design, train, validate, and launch models for behavior cloning and reinforcement learning Build and maintain data ingestion, labeling, and management pipelines to ensure high-quality training datasets Build metrics to evaluate model performance in open loop, simulation, and real-world settings Collaborate with simulation, systems, and infrastructure teams to integrate ML models into real-world autonomous systems Deploy and debug models in real-world environments, addressing latency, hardware constraints, and system integration Qualifications
Practical experience applying machine learning with deep learning frameworks (e.g., PyTorch) to real-world problems Proficiency in Python and familiarity with at least one systems language (e.g., C++, Rust) Familiarity with recent literature and methods in learned behavior policies Practical experience in behavior cloning and/or reinforcement learning Bonus: Experience with diffusion policies, Vision-Language-Action (VLA) models, or related technologies Bonus: Published work in conferences such as ICRA, IROS, CoRL, CVPR, ECCV, ICCV, ICML, NeurIPS About Bedrock
At Bedrock, we have assembled an experienced autonomous technology team with deep expertise scaling breakthroughs across transportation, infrastructure, and enterprise software. Our systems are deployed on heavy machines, learning on real construction sites with emphasis on safety and reliability.
#J-18808-Ljbffr
Machine Learning Engineer with a focus on behavior learning, data-driven behavior policies, and robust data infrastructure. Develop and scale state-of-the-art learning architectures and build data systems that enable reliable, scalable, and reproducible production models. Responsibilities
Design, train, validate, and launch models for behavior cloning and reinforcement learning Build and maintain data ingestion, labeling, and management pipelines to ensure high-quality training datasets Build metrics to evaluate model performance in open loop, simulation, and real-world settings Collaborate with simulation, systems, and infrastructure teams to integrate ML models into real-world autonomous systems Deploy and debug models in real-world environments, addressing latency, hardware constraints, and system integration Qualifications
Practical experience applying machine learning with deep learning frameworks (e.g., PyTorch) to real-world problems Proficiency in Python and familiarity with at least one systems language (e.g., C++, Rust) Familiarity with recent literature and methods in learned behavior policies Practical experience in behavior cloning and/or reinforcement learning Bonus: Experience with diffusion policies, Vision-Language-Action (VLA) models, or related technologies Bonus: Published work in conferences such as ICRA, IROS, CoRL, CVPR, ECCV, ICCV, ICML, NeurIPS About Bedrock
At Bedrock, we have assembled an experienced autonomous technology team with deep expertise scaling breakthroughs across transportation, infrastructure, and enterprise software. Our systems are deployed on heavy machines, learning on real construction sites with emphasis on safety and reliability.
#J-18808-Ljbffr