SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Apptronik is a human-centered robotics company developing AI-powered humanoid robots (Apollo) to support humanity across manufacturing, logistics, healthcare, and beyond. The company operates at the cutting edge of applied AI, tackling the full robotics stack from research to production deployment.
As a Software Engineer for Dexterous Manipulation, you will be a core contributor to Apollo's ability to interact with the world with human-like precision. You will implement, tune, and deploy reinforcement learning and learning-based control algorithms for high-DOF multi-fingered robotic hands, translating state-of-the-art research into reliable, production-grade software that runs in both simulation and on physical hardware.
Key responsibilities include:
- Implement and tune control algorithms for multi-fingered hands, including grasping, in-hand manipulation, and tactile-feedback integration
- Develop and maintain manipulation software with low-latency, reliable execution in the real-time controls stack
- Translate state-of-the-art methods (RL, imitation policies, human-to-robot motion retargeting) into production-grade C++/Python
- Build and refine sim-to-real pipelines using domain randomization and validation in IsaacSim, MuJoCo, or Drake
- Deploy and debug manipulation capabilities on physical robots; diagnose sensor noise, latency, and calibration issues
- Collaborate with hardware and systems engineers to provide feedback on hand performance and sensor/actuator requirements
- Uphold code quality through rigorous testing, documentation, and peer review
Required qualifications:
- BS/MS/PhD in Robotics, Computer Science, Electrical Engineering, or related field
- 3+ years of relevant experience in robotic manipulation or complex motion control (recent PhD graduates considered)
- Dexterous manipulation experience with multi-fingered grasping and high-DOF hand control
- Reinforcement learning for robotic control with reward design, training, and debugging experience
- Strong Python and working C++ for real-time robotic software
- Hands-on experience training and validating policies in physics simulators
- Robotics fundamentals: kinematics, dynamics, and Jacobian-based control
- Proven track record of getting algorithms working on physical hardware, not simulation alone
Nice-to-have skills: teleoperation (VR/haptic) and retargeting, tactile-sensing integration, computer vision (6D pose, point clouds), and end-effector bring-up and calibration.
