Software Engineer - Manipulation

Apptronik • Sunnyvale, CA

1d • $180,000 - $240,000

About The Position

Apptronik is a human-centered robotics company developing AI-powered robots, including Apollo, a humanoid robot designed to collaborate with people. The Software Engineer - Manipulation contributes to enabling reliable, precise interaction between the robot and the world by developing and deploying learning-based manipulation policies, particularly through post-training methods that adapt and improve policies on real tasks and physical hardware.

This role connects cutting-edge research with scalable, reliable production software. Working with simulation, data, hardware, and systems teams, the engineer will take manipulation policies from demonstration data through post-training and toward robust deployment across the robot fleet. The role includes developing visuomotor policies, supporting the policy development and evaluation cycle, and maintaining high standards for software quality.

Requirements

• Strong experience in robotic manipulation, including grasping, in-hand or whole-arm control, and high-DOF motion, with a track record of hardware deployment.
• Hands-on experience training and debugging learned policies, including post-training methods such as RL fine-tuning, distillation, and imitation learning such as DAgger.
• Proficiency in Python, C++, and PyTorch or JAX.
• Experience building real-time robotic software stacks.
• Experience working with demonstration and teleoperation data and building evaluation pipelines for learned policies.
• An MS with 3+ years of relevant experience, or a recent PhD, in Robotics, Computer Science, Electrical Engineering, or a related field.
• Relevant experience focused on learning-based manipulation or a closely related area.
• A proven track record of deploying learned policies on physical hardware after developing them in research or simulation environments.

Nice To Haves

• Experience with physics engines such as IsaacSim, MuJoCo, or Drake for policy training and validation.
• Experience adapting large, general-purpose manipulation policies to specific tasks and embodiments.
• Experience with VR or haptic interfaces and retargeting algorithms for human-in-the-loop control.
• Experience integrating tactile or haptic feedback into manipulation pipelines.
• Familiarity with 6D pose estimation, point cloud processing, or visual servoing.

Responsibilities

• Implement and deploy learning-based manipulation policies for reliable performance on real-world tasks using physical hardware.
• Adapt and improve policies for new tasks and hardware using methods such as RL fine-tuning, policy distillation, and interactive imitation learning such as DAgger.
• Build and maintain post-training data pipelines, including teleoperation and demonstration collection, retargeting, dataset aggregation, and curation.
• Drive policy development from simulation and offline evaluation through transfer and fine-tuning on the robot.
• Develop visuomotor policies for grasping, in-hand manipulation, and whole-arm manipulation, with reliable, low-latency hardware execution.
• Define evaluation metrics and regression tests for policy performance in simulation and on hardware, and use results to guide technical decisions.
• Collaborate with simulation, data, hardware, and systems teams to diagnose system-level issues and develop solutions.
• Maintain code quality through testing, documentation, and peer code reviews.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level