Robotics Software Engineer - Learning-Based Manipulation

Apptronik; Sunnyvale (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Apptronik in Sunnyvale, CA, is hiring a Software Engineer - Manipulation to advance learning-based manipulation policies on real hardware. You will bridge research and production, deploying policies from demonstration data through post-training to robust robot deployment with Apollo fleet.

The role requires an MS with 3+ years in robotics or CS, strong Python/C++, and experience with PyTorch/JAX. Collaboration with simulation, data, hardware, and systems teams is essential to deliver reliable,

Qualifications

• MS with 3+ years of relevant experience or a recent PhD in Robotics, CS, EE, or a related field.
• Experience deploying learned policies on physical hardware.
• Proven track record with learning-based manipulation and policy deployment.

Responsibilities

• Implement and deploy state-of-the-art learning-based manipulation policies with hardware.
• Adapt and improve policies for new tasks and hardware using post-training methods.
• Build data pipelines for teleoperation, demonstration collection, and evaluation.
• Drive development from simulation to robust real-world deployment on the robot.
• Develop visuomotor policies for grasping and manipulation with low latency on hardware.

Skills

Manipulation

Learning-Based Control

Software Engineering

Data & Evaluation

Education

MS + 3+ years experience

PhD (recent)

Tools

IsaacSim

MuJoCo

Drake

Job description

Apptronik in Sunnyvale, CA, is hiring a Software Engineer - Manipulation to advance learning-based manipulation policies on real hardware. You will bridge research and production, deploying policies from demonstration data through post-training to robust robot deployment with Apollo fleet.

The role requires an MS with 3+ years in robotics or CS, strong Python/C++, and experience with PyTorch/JAX. Collaboration with simulation, data, hardware, and systems teams is essential to deliver reliable,