A human-centered robotics company developing AI-powered humanoid robots designed to work alongside people, starting in manufacturing and logistics with future expansion into healthcare and the home, is hiring a Lead Software Engineer to own dexterous manipulation for its flagship platform.
The RoleThis is a core technical leadership role responsible for developing learning-based dexterous control algorithms that unlock advanced manipulation capability on state-of-the-art robotic hand hardware. You will bridge cutting-edge research and scalable production software, applying reinforcement learning, imitation learning, teleoperation retargeting, and classical control to enable high-DOF task performance in both simulation and physical deployment. As technical lead, you will shape core software architecture and directly influence hardware design.
Key Responsibilities- Serve as technical authority for dexterous manipulation, setting the long-term roadmap for hand control and multi-fingered coordination
- Design and enforce foundational software architecture, balancing autonomous logic against high-fidelity teleoperation
- Direct integration of state-of-the-art research, selecting and deploying learning-based policies and vision-integrated systems
- Own sim-to-real strategy, setting standards for high-fidelity simulation and policy transfer to physical hardware
- Drive next-generation hardware specifications, including sensing, degrees of freedom, and torque profiles
- Oversee transition from experimental research to fleet-wide deployment, ensuring production-grade C++/Python performance and reliability
- Set technical culture and mentor senior engineers across the organization
Required Qualifications - Deep expertise in multi-fingered hand control, grasp planning, and in-hand manipulation, with a track record of hardware deployment
- Proficiency in learning-based robotic control (flow/diffusion-based visuomotor policies, reinforcement learning, reward modeling)
- Strong Python skills, with experience building real-time robotic software stacks
- Experience with physics engines (IsaacSim, MuJoCo, or Drake) for policy training and validation
- BS/MS/PhD in Robotics, Computer Science, Electrical Engineering, or related field
- 5+ years relevant experience (3+ with a PhD) in robotic manipulation or complex motion control
- Proven track record deploying algorithms from research/simulation into physical hardware
Differentiators - Strong foundation in kinematics, Jacobian-based control, and constrained optimization
- Teleoperation experience with VR/haptic interfaces and retargeting algorithms
- Tactile sensing integration experience
- Computer vision familiarity (6D pose estimation, point cloud processing, visual servoing)
- Hardware bring-up experience with high-DOF end-effectors
