Robot Learning Engineer - Manipulation
Applied Intuition11 hours ago
Sunnyvale, CA, USAMid Level
H1B sponsor
Base Salary
$150k - $300k/yr
Responsibilities
- Work across the full learning loop for manipulation tasks, including task definition, demonstration collection, data curation, training, real-robot evaluation, and deployment.
- Train and fine-tune manipulation policies ranging from pretrained vision-language-action models to compact task-specific policies.
- Develop repeatable recipes for industrial tasks such as pick-and-place, bimanual handling, and contact-rich assembly, incorporating force or tactile signals where useful.
- Deploy policies on edge compute and validate observation processing, action interfaces, and control timing on physical robots.
- Diagnose failures and use human interventions to improve data, models, and evaluation.
- Improve customer-focused metrics including success rate, cycle time, intervention rate, and the data and time required to reach performance targets.
- Package learned recipes and models for reuse across tasks and robot platforms.
Requirements
- Experience training or fine-tuning a learned manipulation policy and deploying and evaluating it on a physical robot.
- Strong Python and PyTorch skills for maintainable training, evaluation, and deployment code.
- Practical depth in imitation learning and at least one modern policy family, such as vision-language-action models, diffusion policies, or action-chunking transformers.
- Working knowledge of robot kinematics, coordinate frames, camera calibration, and the interface between learned actions and low-level control.
- Ability to diagnose failures using controlled experiments across data, sensing, models, and execution.
- Experience with real systems and comfort handling open-ended problems and communicating tradeoffs.
- Preferred experience with bimanual manipulation, force-controlled insertion, tactile sensing, or dexterous hands.
- Preferred experience with ROS 2, LeRobot, Isaac, or MuJoCo.
- Preferred experience optimizing inference on NVIDIA Jetson or GPU edge systems through model export, compilation, or quantization.
- Preferred experience with reinforcement learning post-training, learning from interventions, or transferring policies across robot platforms.
Benefits
- Full-time employees primarily work from an Applied Intuition office five days per week, with occasional remote-work flexibility; this expectation does not apply to contractors.
- Benefits may include equity, health, dental, vision, life and disability insurance, a 401(k) with employer match, learning and wellness stipends, and paid time off.
- Reasonable accommodations are available for disabled veterans and other applicants with disabilities or medical conditions.
Categories
ML EngineeringRobotics
About Applied Intuition
Applied Intuition builds software tools, infrastructure, and operating systems for developing, testing, and deploying autonomous and driver-assistance systems across automotive, trucking, defense, construction, mining, and agriculture. It sells enterprise software and services including simulation, sensor data management, HD mapping, and a vehicle OS to OEMs and government customers. Founded in 2017 and headquartered in Sunnyvale, California, it counts 18 of the top 20 global automakers and the U.S. military among its users.