Member of Technical Staff, Robotics Engineer

Workman Labs; New York (NY); Hybrid; USD 270,000 - 370,000; Full time

Job summary

Runway in New York is seeking a Member of Technical Staff, Robotics Engineer to connect world models to physical robots and extend the company's simulation capabilities to real hardware.

You will own the deployment loop for learned policies on real robot arms, diagnose failures, and help design data collection and evaluation protocols while collaborating with research to improve policy success.

Qualifications

• Deployment of software on real robot hardware and iteration to fix issues on physical robots.
• Fluency in action/command spaces, control frequencies, and observation pipelines.
• Ability to reconfigure a robot workspace and trace policy failures quickly.

Responsibilities

• Own the deployment loop for learned policies (VLAs, diffusion policies, World Action Models) on real robot arms: inference serving, action decoding, controller integration, latency budgets, and safety limits
• Diagnose real-world policy failures - determining whether the problem is data coverage, camera/proprioception mismatch, or execution - and fix at the right layer with research
• Design demonstration data collection protocols (task setup, camera placement, teleop conventions) to teach world models effectively
• Partner with research to run controlled experiments linking world model representations, data composition, and fine-tuning to physical success rates
• Define and run physical evaluation protocols so results are trustworthy and comparable across policy iterations
• Adapt policy recipes to partner hardware and new embodiments

Skills

Real robot deployment

Software-to-robot interface

Policy deployment experience

Hardware-in-loop troubleshooting

Job description

Member of Technical Staff, Robotics Engineer

Runway is hiring a robotics engineer in New York to connect its world models to physical robots, part of the company's push from video generation into general-purpose simulation.

$270,000 – $370,000 / yr

Location

New York, NY

On-site

Seniority

—

Compared with 15 other Research roles: Common across similar roles Unique to this role

What you'll do

Responsibilities

• Own the deployment loop for learned policies (VLAs, diffusion policies, World Action Models) on real robot arms: inference serving, action decoding, controller integration, latency budgets, and safety limits
• Diagnose real-world policy failures - determining whether the problem is data coverage, camera/proprioception mismatch, or execution - and partner with the research team to fix it at the right layer
• Design demonstration data collection protocols (task setup, camera placement, teleop conventions) that produce data our world models can actually learn from - working with our existing teleop and lab infrastructure Common
• Partner with research to run controlled experiments connecting world model representations, data composition, and fine-tuning recipes to physical success rates Common
• Define and run physical evaluation protocols so results are trustworthy and comparable across policy iterations
• Adapt our policy recipe to partner hardware and new embodiments Unique

What you'll need

Experience

• You have personally deployed software on real robot hardware and iterated to make it work - whether learned policies, motion planning, classical control, or perception-driven manipulation. You can walk through a specific system you shipped, what broke on the physical robot that didn't break in sim or testing, and how you fixed it. Unique
• Fluency in the software-to-robot interface: action/command spaces, control frequencies, observation pipelines, calibration, and how each affects real-world behavior
• Comfort working at the intersection of software and physical systems: you can reconfigure a robot workspace and trace a policy failure in the same afternoon Unique
• Bonus: direct experience deploying learned policies (VLAs, diffusion policies) on real hardware; experience with video/multimodal generative models or world models Common