Role overview
Job description
- Develop whole-body control and manipulation capabilities for humanoids and quadrupeds with arms, coordinating base, torso, and arm motion as a single system
- Take specific field scenarios from concept to repeatable execution on hardware, interacting with the built environment and handling objects and tools
- Build learning based and model based manipulation policies and integrate them tightly with perception and locomotion
- Train manipulation policies from demonstration data and adapt vision language action (VLA) foundation models to our robots and tasks, then make them work on hardware
- Design grasp, contact, and force interaction strategies that hold up across varied objects, surfaces, and environments, with interaction forces kept safe for people and equipment nearby
- Harden behaviors so they succeed across repeated runs, changing lighting, object variation, and real site conditions
- Build simulation environments and evaluation pipelines for manipulation, and use field data to close the gap between simulation and the real world
- Deploy on physical robots and iterate rapidly through lab testing and field validation
- Work closely with locomotion, perception, and systems engineers to deliver end to end capabilities
- Master’s degree or higher in Robotics, Computer Science, Engineering, or related field (PhD strongly preferred)
- Deep expertise in robot manipulation or whole-body control
- 2+ years of experience developing and deploying manipulation behaviors on real robotic systems (preferred)
- Hands-on experience with robot arms, hands or grippers, and humanoid or mobile manipulation platforms
- Solid understanding of kinematics, dynamics, contact modeling, and force control
- Experience with manipulation planning and control, such as trajectory optimization or model predictive control (MPC)
- Experience with learning based manipulation, such as imitation learning, reinforcement learning (RL), or vision language action models
- Proficiency with simulation tools such as Isaac Lab, MuJoCo, or Drake
- Experience integrating perception for manipulation
- Strong Python and/or C++ development skills in Linux-based development environments
- Familiarity with machine learning frameworks (PyTorch, JAX, TensorFlow)
- A passion for building things that move in the real world
- 3+ years of experience in an industry or startup robotics setting
- Experience with loco-manipulation on legged platforms or whole-body model predictive control for humanoids
- Experience fine tuning or deploying vision language action models on real robots
- Experience building teleoperation and demonstration data collection pipelines at scale
- Experience with cross embodiment or generalist manipulation policies that transfer across robots and tasks
- Experience with dexterous multi fingered hands, or with tactile and force torque sensing in closed loop manipulation
- Experience optimizing and deploying learning based controllers on resource constrained robotic platforms (ONNX Runtime, NVIDIA TensorRT, real time onboard inference)
- Publications or open-source contributions in manipulation, whole-body control, or robot learning (e.g., CoRL, RSS, ICRA, IROS)
- Familiarity with ROS/ROS2 or custom middleware for real-time control
- Experience debugging sim-to-real issues at scale
About this listing
- Source: FieldAI's official careers site (via Lever) · last confirmed on the source 27 Oct 2026
- Posted 5 Sept 2026
Jobiba does not charge job seekers. Never pay to apply or share OTPs, card or bank details.
What they are looking for
Skills & requirements
Department · Engineering
Hiring company
FieldAI
FieldAI is the leader in deploying general-purpose robots in unstructured environments, providing a universal brain that works across many robots, and many tasks.
Related opportunities
Similar active roles
Relevant, currently active roles for this market.
$100K – $200K/yr
$100K – $200K/yr
$100K – $200K/yr
$100K – $230K/yr
$100K – $200K/yr
🔔 Get job alerts
New Robotics Autonomy Engineer jobs in Irvine, California, United States, straight to your inbox.
No spam · Unsubscribe anytime