Research Engineer, Robotics - Roboticist
The Allen Institute · Seattle, WA
About this role
**Research Engineer, Robotics – Roboticist** **Location / Work setup** - Expected to work from our offices in **Seattle**. On-site requirements vary by position and team. If you have questions, ask your recruiter. **Compensation** - **Base salary range:** **$128,880 – $193,320** - **Bonus plans** available to provide a competitive compensation package. --- ## Who You Are You will **own the control stack** on physical robots and the path from **simulation to real hardware**. This is primarily a **controls role**: you’ll bring up and tune **real-time, torque-level control** on robotic arms, multi-fingered hands, bimanual systems, and humanoids—making them stable and safe enough for researchers to run experiments daily. You’ll also build the interfaces that learned policies plug into. You will additionally **design and build the hardware** the research needs (e.g., end-effectors and test rigs), and work closely with research scientists and the simulation team so that simulation results translate reliably to hardware. --- ## Who We Are The **Robotics team at Ai2** (led by **Dieter Fox**) uses scalable simulation to study how **foundation models scale and generalize for robotics**. Focus areas include: - Manipulation - Humanoid and whole-body control - Large-scale simulated training - Sim-to-real transfer - Robot foundation models and skill learning They publish at **CoRL, ICRA, RSS, CVPR, NeurIPS, ICLR, and ICML**, and everything they build is **open source**. --- ## Your Next Challenge - **Build and own the real-time control stack**: joint, impedance, operational-space, and torque control on torque-controlled arms, hands, and humanoids—plus motion planning, safety layers, and policy interfaces. - **Stabilize whole-body controllers** for humanoids and bimanual systems (e.g., **QP/MPC-based** control), including state estimation (IMU/encoders/force-torque), contact handling, and sim-to-real transfer for locomotion and loco-manipulation. - **Lead robot setup and tuning** across arms, grippers, multi-fingered hands, humanoids, cameras, and tactile sensors. - **Diagnose stability, latency, and contact issues** across hardware, firmware, control, and learned policies using system identification and dynamics models. - **Design and build lab hardware**: end-effectors, fingertips, sensor mounts, fixtures, and test rigs (CAD → 3D printing/machining), including integrating cameras and tactile sensors. - **Build runtime and tooling**: teleoperation/data collection, logging, monitoring, deployment, and operator-facing tools. - **Contribute to open-source releases and publications**. --- ## What You’ll Need ### Minimum Qualifications - **Master’s + 3+ years** experience, or **PhD**, in robotics, control, or related field. Strong candidates with a **bachelor’s + 3+ years industry** experience are also considered. - **Controls**: implemented and tuned real-time controllers (joint/impedance/operational-space/torque) on physical robots; strong grounding in rigid-body dynamics, control theory, stability analysis, and system identification. - **Whole-body / floating-base control**: understanding of floating-base dynamics, contact constraints, inverse dynamics; experience with at least one of **QP whole-body control**, **operational-space control**, or **MPC** on hardware or in high-fidelity simulation. - **Manipulation**: hands-on real-robot manipulation (bring-up, calibration, control of arms with grippers/hands). - **System design**: end-to-end
Listing freshness
CronJobs last confirmed this listing 47m ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.