Research Engineer, Robotics - Roboticist
Seattle-based nonprofit AI research institute developing openly released models, datasets, tools, and AI applications for science, the environment, and robotics.
Funding history
About Allen Institute for AI (Ai2)
Ai2 is a nonprofit AI research institute founded by Paul Allen in 2014. It develops openly documented language and multimodal models, training data and code, plus applied AI systems for scientific discovery, planetary intelligence, and conservation.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own the control stack on physical robots and the path from simulation to them. You will bring up and tune real-time torque-level control on arms, multi-fingered hands, bimanual systems and humanoids, and build interfaces for learned policies. You will also design hardware such as end-effectors and test rigs, and work closely with research scientists and the simulation team.
Requirements
- Master's with 3+ years of experience, or PhD, in robotics, control or related field; or bachelor's with 3+ years industry experience
- Experience implementing and tuning real-time controllers on physical robots
- Knowledge of floating-base dynamics and QP-based whole-body control, operational-space control or MPC
- Hands-on real-robot manipulation experience
- Robot software system design with 500 Hz to 1 kHz control loops; strong Python and solid real-time C++
- Mechanical design and CAD experience with design-for-manufacturing
- Experience training or deploying learned policies; PyTorch and a simulation ecosystem (Isaac Lab, MuJoCo)
- Full-stack debugging and clear communication
Responsibilities
- Build and own the real-time control stack for arms, hands and humanoids
- Bring up, tune and stabilize whole-body controllers for humanoids and bimanual systems
- Lead setup, calibration, maintenance and tuning of robots
- Diagnose stability, latency and contact problems across hardware, firmware, control and learned policy
- Design and build end-effectors, fingertips, sensor mounts, fixtures and test rigs
- Build runtime and tooling for teleoperation, data collection, logging, monitoring and deployment
- Contribute to open-source releases and publications
Benefits
- Medical, dental, vision, life and AD&D insurance
- Short-term and long-term disability and employee assistance program
- Voluntary life, AD&D, HSA, HRA and FSA plans
- 401k plan
- $125 per month commuting or internet stipend
- $200 per month fitness and wellbeing stipend
- Up to 10 sick days, 7 personal days, 20 vacation days and 12 paid holidays
- Annual bonuses and long-term incentive plan