Machine Learning Engineer

The role

You will work on multimodal perception, VLA training, robotics post-training, and downstream policy evaluation. This role involves building systems for data collection, validation, annotation, and evaluation at the intersection of machine learning, data infrastructure, and robotics.

What you will do

• Build systems for multimodal perception, annotation, dataset QA, and robotics evaluation
• Publish research on multimodal data by fine-tuning and evaluating VLA models on downstream robotics tasks and policy performance
• Build post-training and reinforcement learning systems around robotics failure modes and corrective demonstrations
• Work across video understanding, tracking, pose estimation, temporal modeling, and multimodal alignment
• Develop tooling for benchmarking, observability, and temporal efficiency
• Prototype quickly, ship rapidly, and iterate from real-world robotics deployments and research feedback

Required qualifications

• Strong ML engineering fundamentals across robotics, computer vision, and perception systems
• Experience with video understanding, tracking, pose estimation, robotics, or real-world sensor systems
• Strong technical intuition and ability to move quickly in ambiguous research environments
• Passionate, mission-driven individuals who have demonstrated exceptional ownership in previous work
• Engineers who want their work to directly impact the next frontier of physical AGI

Nice to have

• Published research or production experience in robotics, embodied AI, reinforcement learning, motion capture, or vision systems

About the company

Human Archive is a research lab focused on modeling human embodied intelligence. Founded by Stanford and UC Berkeley researchers, the lab builds custom hardware products, deploys them globally, and publishes research.