Founding AI Research Engineer (Robot Learning)

TL;DR

Founding AI Research Engineer (Robot Learning): Developing and deploying learned components for autonomous construction robots with an accent on VLA models, imitation learning, and edge optimization. Focus on building a data flywheel for contact-rich manipulation and optimizing model latency for real-time hardware deployment.

Location: Onsite in New York City

Company

hirify.global is building physical AI for the built world, creating robots that autonomously finish building interiors at production quality.

What you will do

• Train and deploy VLA models for contact-rich manipulation using imitation learning infrastructure.
• Build the data flywheel, including teleoperation pipelines, DAgger-style correction, and demonstration curation.
• Research and prototype world models for surface state prediction, spray dynamics, and anomaly detection.
• Design offline evaluation metrics to predict real-world finishing quality before deployment.
• Optimize models for edge deployment on Jetson AGX Orin using TensorRT, latency profiling, and memory budgeting.
• Design the interface where learned policies propose actions and deterministic safety layers enforce constraints.

Requirements

• Degree (BS/MS/PhD) in CS, Robotics, ML, or equivalent experience shipping learned systems on physical robots.
• Strong proficiency in Python and PyTorch, including experience modifying research codebases.
• Experience in at least two of: imitation learning, RL, vision-language models, robot learning from demonstration, or sim-to-real.
• Proven track record of deploying ML on real hardware and debugging policy failures on actual robots.
• Working knowledge of ROS2 or equivalent robotics middleware.
• Experience with simulation systems like Isaac Sim and GPU optimization (TensorRT, ONNX, CUDA).

Nice to have

• Hands-on experience with VLA architectures (π0, OpenVLA, RT-2, Octo) or foundation model fine-tuning.
• Expertise in teleoperation data collection and DAgger/HG-DAgger pipelines.
• Experience with world model architectures such as DreamerV3, V-JEPA, or latent dynamics models.
• Experience in construction, manufacturing, or contact-rich industrial domains.
• Publications at CoRL, RSS, ICRA, or NeurIPS.