Robot Learning Engineer: Manipulation on Real Robots

Hardware FYI; Sunnyvale (CA); Hybrid; USD 140,000 - 210,000; Full time

Job summary

Applied Intuition, Inc. is building a robot learning platform on Dana, its physical AI stack.

The robotics team develops policies and data infrastructure to enable robot autonomy on customer lines, including training, evaluating, and deploying policies on real robots performing industrial tasks. You will work on manipulation policies from task definition to reliable real-robot execution, training and fine-tuning models, and ensuring performance beyond offline benchmarks.

Qualifications

• 1+ years of professional experience.
• Bachelor's degree in Computer Science, Software Engineering, or equivalent.
• Trained or fine-tuned a learned manipulation policy and deployed/evaluated it on a physical robot.
• Strong Python and PyTorch skills with maintainable training, evaluation, and deployment code.
• Practical depth in imitation learning and at least one modern policy family.
• Working knowledge of robot kinematics, coordinate frames, camera calibration, and learned-action interfaces.
• Habit of diagnosing failures with controlled experiments across data, sensing, model, and execution.
• Comfort taking on open-ended problems and communicating tradeoffs clearly to teammates.

Responsibilities

• Work on the full learning loop for manipulation tasks: task definition, demonstration collection, data curation, training, real-robot evaluation, and deployment.
• Train and fine-tune manipulation policies, from large pretrained models to compact task-specific policies, choosing the right approach.
• Develop repeatable recipes for industrial tasks such as pick-and-place, bimanual handling, and contact-rich assembly with force/tactile signals when helpful.
• Deploy policies on edge compute and validate observation processing, action interfaces, and control timing on the robot.
• Turn failures and human interventions into better data, better models, and better evaluation.
• Measure success metrics like accuracy, cycle time, intervention rate, and data/time needed to reach targets, improving task after task.
• Package recipes and models so future tasks start from learned knowledge.

Skills

Python

PyTorch

Imitation learning

Robot kinematics

Experiment-driven debugging

Open-ended problem solving

Communication

Education

Bachelor's degree in Computer Science or equivalent

Tools

ROS 2

Isaac

MuJoCo

NVIDIA Jetson

LeRobot

Job description

Applied Intuition, Inc. is building a robot learning platform on Dana, its physical AI stack.

The robotics team develops policies and data infrastructure to enable robot autonomy on customer lines, including training, evaluating, and deploying policies on real robots performing industrial tasks. You will work on manipulation policies from task definition to reliable real-robot execution, training and fine-tuning models, and ensuring performance beyond offline benchmarks.