Robotics Research Engineer

Title: Robotics Research Engineer

Duration: 12+Months (Extension)

Location: New York (On-Site)

Job Description

We are building physically reliable, safety-critical humanoid robots for real manufacturing environments. You will work at the intersection of world models, VLAs, and Deep RL, developing algorithms and control systems that enable humanoids to perform robust manipulation, locomotion, and long-horizon task execution in dynamic, unstructured industrial settings. Your work will directly shape our autonomy roadmap and impact real-world deployment.

Core Research:

• Design and implement next-generation world models, VLA policies, and Deep RL algorithms for dynamics understanding, uncertainty reasoning, and long-horizon planning. Build physics-consistent generative models (latent dynamics, V-JEPA-style architectures, diffusion-based approaches) for predictive control and sim-to-real transfer.
• Develop visuomotor policies for industrial manipulation and locomotion. Apply hybrid control approaches, model-based RL, diffusion policies, MPC hybrids to stabilize behavior under real-world distribution shift, faults, and safety constraints.

Simulation & Deployment:

• Use Isaac Sim, MuJoCo, and custom simulators to generate training data and evaluate policies at scale. Build physics-aware pipelines integrating contacts, proprioception, force/torque feedback, and language-conditioned planning. Deploy policies on real humanoids, debugging failure modes and building reliable recovery behaviors. You will ship code to real robots in real facilities and publish papers.

AI-Augmented Engineering:

• Use Claude Code, coding agents, and AI-assisted workflows to parallelize research and engineering tasks. We expect you to move at a pace that would be impossible without these tools, running multiple experiments, debugging deployment issues, writing infrastructure, and iterating on research simultaneously. If you're not already using AI tools to 3-5x your output, this role will feel very fast.

What you'll get:

• Collaborate with top researchers and professors across AI, physics, and robotics. Impact real deployments in industrial facilities. Competitive compensation, equity, and large-scale compute.

Who we're looking for:

• BS, MS, or PhD in ML, Robotics, CS, Physics, or related fields from a top-10 program. We care about what you've built, not what degree you hold, but we expect elite technical foundations.
• Deep expertise in one or more of: world models and latent dynamics, VLA architectures (RT-X, Pi-0 class), Deep RL (actor-critic, model-based RL, large-scale RL), generative modeling (diffusion, autoregressive, latent video models), hands-on deployment of learned policies on physical robots, multi-contact control, whole-body planning, or balance control.
• Strong engineering skills in Python, PyTorch, and scalable training systems.

What makes you stand out:

• You've won or placed at hackathons, robotics competitions, or similar high-intensity build events. You've shipped something real under extreme time pressure and enjoyed it. You use Claude Code, Cursor, or similar AI-assisted development tools daily and have strong opinions about how to use them well. You're the person who runs three things in parallel while debugging a fourth. You have a bias toward building over theorizing, and you treat pace as a competitive advantage.