Apptronik
Software Engineer - Dexterous Manipulation
About this role
Apptronik seeks a Software Engineer to develop and deploy reinforcement learning-based control algorithms for high-DOF robotic hands. You'll translate cutting-edge manipulation research into production C++/Python code, build sim-to-real pipelines, and get complex grasping and in-hand manipulation tasks working reliably on physical Apollo robots.
What you'll do
- Implement and tune control algorithms for multi-fingered hands including grasping, in-hand manipulation, and tactile feedback
- Develop low-latency, reliable manipulation software within real-time controls stack
- Convert RL, imitation learning, and motion retargeting research into production-grade code
- Build and refine sim-to-real pipelines using IsaacSim, MuJoCo, or Drake with domain randomization
- Deploy, test, and debug manipulation on physical robots; diagnose sensor and latency issues
- Collaborate with hardware and systems teams on hand performance and sensor/actuator requirements
What they're looking for
- Dexterous manipulation and multi-fingered hand control
- Reinforcement learning for robotic control (reward design, training, debugging)
- Python and C++ for real-time robotics
- Physics simulation (IsaacSim, MuJoCo, Drake)
- Robotics fundamentals (kinematics, dynamics, Jacobian control)
- Hardware-to-sim validation and deployment experience
- Imitation learning and diffusion policies (preferred)
- Teleoperation, tactile sensing, or computer vision (nice-to-have)
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Apptronik
Apptronik builds Apollo, a humanoid robot designed for manufacturing, logistics, and other industrial applications. The company is hiring firmware engineers, software engineers, controls specialists, and networking engineers to develop embedded systems, motor control, motion pipelines, and wireless connectivity that power the robot's dexterous manipulation and autonomous operation.
- Website
- apptronik.com
Likely interview questions
- Describe a dexterous manipulation project where you took an algorithm from simulation to physical hardware—what were the key gaps and how did you address them?
- How do you approach reward design and training for RL-based manipulation tasks? Walk us through a specific example.