Founding Robot Learning Research Lead

About Origin

Originis building Physical AI for the built world - starting with autonomous robots for Interior Construction. We are building Construction Action Models which allows our modular robots to learn, adapt and work in unstructured construction job site.

Our robots are already deployed on live sites in New York City, helping accelerate schedules for large-scale commercial projects while improving safety and predictability on the job site. Backed by Tier-1 investors, Origin is working to close the gap between America’s surging demand for housing, data centers, and manufacturing infrastructure, and the construction industry’s growing labor shortage.

The Role

Our system runs a Multi Agent Action Expert architecture: classical precision algorithms orchestrated alongside learned policies. The job is systematically expanding the learned components while keeping the system production-safe. You own the full lifecycle of learned components on OG-1: from data collection and model training through edge deployment on Jetson AGX Orin. Every research project will have a deployment milestone. This is not a lab position.

What you will own?

• Define the technical roadmap forRobot Learning and Embodied AI.
• Build and deploy learned policies for real-world mobile manipulation and contact-rich tasks.
• Developimitation learning, reinforcement learning, VLA, and learning-from-demonstrationsystems.
• Fine-tune and adapt open-source VLA/foundation models for our robot platform.
• Build scalableteleoperation → dataset → training → evaluation → deploymentloops.
• Develop DAgger / HG-DAgger and human-in-the-loop data collection pipelines.
• Build simulation environments and training pipelines usingNVIDIA Isaac Sim / Isaac Lab.
• Develop sim-to-real strategies including domain randomization, system identification, and real-world policy adaptation.
• Exploreworld models and latent dynamics modelsfor planning, prediction, and policy learning.
• Integrate learned policies with our existing ROS2 perception, planning, manipulation, control, and safety stack.
• Optimize inference for deployment on edge GPUs usingTensorRT, ONNX, CUDA, profiling, quantization, and related techniques.
• Debug policies on physical robots: latency, observation drift, calibration errors, distribution shift, contact instability, action representation, control frequency, and hardware-induced failures.
• Establish rigorous evaluation for learned systems across simulation, replay datasets, and physical robot experiments.
• Build and mentor the Robot Learning team as we scale.

Our broader robot architecture already spans perception, manipulation, planning, ROS integration, simulation, force/impedance control, quality assessment, and autonomous recovery.

Requirements

• BS/MS/PhD in CS, Robotics, ML, or related field fromStanford, MIT, UC Berkeley, CMU, Georgia Tech, ETH Zürich, or UPenn, or equivalent exceptional experience shipping learned systems on physical robots.

• PhD:minimum2 yearsrelevant experience.Without PhD:minimum5 yearsrelevant experience.
• StrongPython and PyTorch; comfortable modifying research codebases and open-source VLA implementations.
• Experience in at least two of:imitation learning, RL, VLA/VLMs, robot learning from demonstration, sim-to-real.
• Track record deploying ML onreal robots— not just training policies, but debugging why they fail on actual hardware.
• Working knowledge ofROS2or equivalent robotics middleware.
• Experience with simulation systems such asNVIDIA Isaac Sim / Isaac Lab.
• GPU inference profiling and optimization (TensorRT, ONNX, CUDA); understand the impact of policy latency on real-time robot control.

Strong Plus

• Hands-on with VLA architectures such asπ0/π0.5, OpenVLA, RT-2, Octo, or robotics foundation-model fine-tuning.
• Teleoperation data collection andDAgger / HG-DAggerpipelines.
• World models such asDreamerV3, V-JEPA, or latent dynamics models.
• Experience withcontact-rich manipulation, construction, manufacturing, or industrial robotics.
• Publications atCoRL, RSS, ICRA, NeurIPS— valued, but equivalent shipped work on real robots counts.