Founding Robot Learning Research Lead

Origin•San Francisco, CA

19h•Onsite

About The Position

Origin is building Physical AI for the built world, starting with autonomous robots for Interior Construction. We are developing Construction Action Models that enable our modular robots to learn, adapt, and operate in unstructured construction environments. Our robots are currently deployed on live sites in New York City, contributing to accelerated schedules for large-scale commercial projects while enhancing safety and predictability. Backed by Tier-1 investors, Origin aims to address the construction industry's labor shortage and meet the increasing demand for housing, data centers, and manufacturing infrastructure. The role involves expanding the learned components of our Multi-Agent Action Expert architecture, which combines classical algorithms with learned policies, while ensuring production safety. The successful candidate will manage the entire lifecycle of learned components on the OG-1 robot, from data collection and model training to edge deployment on Jetson AGX Orin. Every research project will have a deployment milestone, making this a hands-on, non-laboratory position.

Requirements

BS/MS/PhD in CS, Robotics, ML, or related field from Stanford, MIT, UC Berkeley, CMU, Georgia Tech, ETH Zürich, or UPenn, or equivalent exceptional experience shipping learned systems on physical robots.
PhD: minimum 2 years relevant experience. Without PhD: minimum 5 years relevant experience.
Strong Python 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 on real robots — not just training policies, but debugging why they fail on actual hardware.
Working knowledge of ROS2 or equivalent robotics middleware.
Experience with simulation systems such as NVIDIA Isaac Sim / Isaac Lab.
GPU inference profiling and optimization (TensorRT, ONNX, CUDA); understand the impact of policy latency on real-time robot control.

Nice To Haves

Hands-on with VLA architectures such as π0/π0.5, OpenVLA, RT-2, Octo, or robotics foundation-model fine-tuning.
Teleoperation data collection and DAgger / HG-DAgger pipelines.
World models such as DreamerV3, V-JEPA, or latent dynamics models.
Experience with contact-rich manipulation, construction, manufacturing, or industrial robotics.
Publications at CoRL, RSS, ICRA, NeurIPS — valued, but equivalent shipped work on real robots counts.

Responsibilities

Define the technical roadmap for Robot Learning and Embodied AI.
Build and deploy learned policies for real-world mobile manipulation and contact-rich tasks.
Develop imitation learning, reinforcement learning, VLA, and learning-from-demonstration systems.
Fine-tune and adapt open-source VLA/foundation models for our robot platform.
Build scalable teleoperation → dataset → training → evaluation → deployment loops.
Develop DAgger / HG-DAgger and human-in-the-loop data collection pipelines.
Build simulation environments and training pipelines using NVIDIA Isaac Sim / Isaac Lab.
Develop sim-to-real strategies including domain randomization, system identification, and real-world policy adaptation.
Explore world models and latent dynamics models for 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 using TensorRT, ONNX, CUDA, profiling, quantization, and related techniques.
Debug policies on physical robots, addressing issues like 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.