Research Engineer, Robotics - Roboticist

The Allen Institute for Artificial Intelligence•Seattle, WA

21h•$128,880 - $193,320•Onsite

About The Position

The Research Engineer, Robotics will own the real-time control stack for Ai2’s physical robots and the path from simulation to hardware. This is primarily a controls role, involving the bring-up and tuning of real-time, torque-level control on arms, multi-fingered hands, bimanual systems, and humanoids. The engineer will make hardware stable and safe for daily research experiments and build interfaces that learned policies can use. The role also designs and builds research hardware, from end-effectors to test rigs, and works closely with research scientists and the simulation team to transfer simulated behavior reliably to physical robots. Ai2’s Robotics team uses scalable simulation to study how foundation models scale and generalize for robotics. Its work includes manipulation, humanoid and whole-body control, large-scale simulated training, sim-to-real transfer, robot foundation models, and skill learning. The team publishes at major research venues and releases its work as open source. The role is expected to work from Ai2’s Seattle offices; on-site requirements vary by position and team. The base salary range is $128,880–$193,320, with bonus plans in addition to base salary. The position includes collaboration on research, open-source releases, and publications. Humanoid whole-body control and experience with Unitree platforms are especially valuable as the lab’s humanoid and whole-body work grows.

Requirements

Master’s degree and at least 3 years of experience, or a PhD, in robotics, control, or a related field; candidates with a bachelor’s degree and at least 3 years of industry experience are also considered.
Experience implementing and tuning real-time controllers on physical robots, such as joint, impedance, operational-space, or torque control; strong grounding in rigid-body dynamics, control theory, stability analysis, and system identification.
Understanding of floating-base dynamics, contact constraints, and inverse dynamics, with experience in at least one of QP-based whole-body control, operational-space control, or MPC on hardware or in a high-fidelity simulator.
Substantial hands-on experience with real-robot manipulation, including bring-up, calibration, and control of arms with grippers or hands.
Experience designing end-to-end robot software systems, including control loops at 500 Hz to 1 kHz, state estimation, data flow, and interfaces between planning, perception, and learning; ability to reason about latency, reliability, and failure modes.
Strong Python and solid real-time C++ skills.
Experience designing and building hardware used on a real robot, such as end-effectors, mounts, fixtures, or rigs.
CAD skills using SolidWorks, Fusion 360, Onshape, or similar, and design-for-manufacturing experience for 3D printing or machining.
Experience training or deploying learned policies, such as imitation learning, reinforcement learning, or VLA, on real robots; familiarity with PyTorch and at least one simulation ecosystem such as Isaac Lab or MuJoCo.
Ability to debug across perception, control, and hardware, and communicate clearly with a structured, systems-oriented approach.

Nice To Haves

Hands-on humanoid whole-body control on hardware, including locomotion, loco-manipulation, balance, and contact-rich tasks; experience bringing up and deploying on Unitree G1, H1, similar platforms, or comparable humanoids.
Depth in control theory, including Lyapunov and passivity-based methods, contact-stable and compliant control, dynamical-systems approaches to motion generation, and reduced-order models such as centroidal dynamics, SRBD, or LIPM, with hardware application experience.
Experience training RL locomotion or loco-manipulation policies in GPU-accelerated simulators such as Isaac Lab or MuJoCo Warp and deploying them stably on real humanoids, including domain randomization, actuator modeling, and safety wrappers.
Whole-body state estimation and sensor fusion using IMUs, joint encoders, force/torque sensors, contact estimation, or Kalman filtering.
Experience with bimanual systems, multi-fingered hands, or tactile sensing.
Teleoperation systems, including VR, leader-follower arms, hand and body tracking, whole-body retargeting, and large-scale data collection.
Experience with robotics middleware and infrastructure such as ROS 2, DDS, Zenoh, real-time Linux, containerization, or CI/CD.
Hand-eye and multi-camera calibration, depth sensing, or 3D perception on hardware.
Open-source contributions or publications at robotics venues such as CoRL, RSS, ICRA, IROS, or Humanoids.

Responsibilities

Build and own the real-time control stack across robot embodiments, including joint, impedance, operational-space, and torque control, motion planning, safety layers, and interfaces for learned policies.
Bring up, tune, and stabilize whole-body controllers for humanoids and bimanual systems, including QP- or MPC-based control, state estimation, contact handling, and fall or fault recovery.
Transfer learned locomotion and loco-manipulation policies from simulation to physical robots.
Lead setup, calibration, maintenance, and tuning of arms, grippers, multi-fingered hands, humanoids, cameras, and tactile sensors across single-arm, bimanual, mobile, and legged platforms.
Diagnose stability, latency, and contact problems across hardware, firmware, control, and learned policies; use system identification and dynamics models to improve real-world reliability.
Design and build lab hardware, including end-effectors, fingertips, sensor mounts, fixtures, and test rigs, from CAD through 3D printing or machining; integrate cameras, tactile sensors, and hands.
Build robot runtime and supporting tools for teleoperation, data collection, logging, monitoring, deployment, and operator workflows.
Contribute to open-source releases and publications.

Benefits

Medical, dental, and vision coverage for team members and their families.
Basic life insurance and basic accidental death and dismemberment insurance.
Short-term and long-term disability coverage.
Employee assistance program.
Voluntary life insurance and voluntary accidental death and dismemberment programs.
Health savings account, healthcare reimbursement arrangement, and healthcare and dependent care flexible spending account plans.
Company 401(k) plan.
$125 per month to assist with commuting or internet expenses.
$200 per month for fitness and wellbeing expenses.
Up to ten sick days, seven personal days, and 20 vacation days per year.
Twelve paid holidays per year.
Annual bonuses and participation in a long-term incentive plan.
Paid family leave.
Learning and ongoing education opportunities.