Research Scientist Intern

Clone Robotics; Mountain View (CA); On-site; USD 34,440,000 - 61,992,000; Full time

Benefits offered by this job

3-month internship

Internship extension possibility to FT

On-site Mountain View lab

Hardware access to muscle-driven hands

GPU compute resources

Job summary

Clone Robotics in Mountain View is seeking an ambitious intern to work across the full stack of robotics research, from simulation to hardware bring‑up. You will train policies for dexterous, tendon‑driven hands and contribute to improving simulators and domain randomization methodologies.

You will collaborate with research teams to push toward human‑like control on real hardware, with opportunities to extend the internship to a full‑time role and gain access to state‑of‑the‑art robotics

Qualifications

• Fundamentals in reinforcement learning and deep learning with hands-on PyTorch or JAX.
• Experience training RL policies, ideally for robotics or continuous control.
• Comfort with physics simulators (MuJoCo, Isaac Sim, Brax, Genesis).
• Willingness to work with real hardware; robotics is empirical.

Responsibilities

• Train RL policies in simulation for dexterous, in‑hand manipulation on musculo‑tendon driven robots.
• Improve fidelity of simulation models for compliant, high‑DOF musculoskeletal systems.
• Design metrics and benchmarks to evaluate policies in simulation and on real hardware.
• Build and harden sim‑to‑real pipelines: domain randomization and system identification.
• Deploy policies on real hardware and debug latency, friction, hysteresis, sensing, and other issues.

Skills

Reinforcement learning

PPO / SAC

PyTorch or JAX

Training RL policies

Robotics simulation

Dexterous manipulation

Domain randomization

Hands-on robotics

Research publishing

Education

BS, MS, or PhD in CS/Robotics/EE/ML

Tools

MuJoCo

Isaac Sim / Lab

Brax

Genesis

PyTorch

JAX

Job description

You'll work end-to-end: from training policies in simulation all the way to debugging what breaks when the policy meets real hardware. The work spans simulation fidelity, policy learning, and empirical bring‑up on muscle‑driven robots.

Policy training & simulation

• Train RL policies in simulation — MuJoCo, Isaac, or similar — fordexterous, in‑hand manipulation on musculotendon‑driven robots.
• Improve the fidelity of our simulation models ofcompliant, high‑DOF musculoskeletal systems: the closer the sim, the smaller the reality gap.
• Designmetrics and benchmarks to evaluate policies in open loop, in simulation, and on the real robot — so progress is measurable at every stage.
• Build and hardensim‑to‑real pipelines: domain randomization, system identification, and actuator modeling for MTUs and tendon routing.
• Deploy policies on real hardware, thendebug what breaks: latency, friction, hysteresis, sensing, and everything the simulator didn't warn you about.

Requirements

We care about fundamentals and hands‑on experience with real systems. Strong theoretical grounding matters, but so does comfort operating outside the simulator.

Required

• Currently pursuing or recently completed aBS, MS, or PhD in CS, Robotics, EE, ML, or a related field.
• Strong fundamentals inreinforcement learning— e.g. PPO, SAC — and deep learning, with hands‑onPyTorch or JAX.
• Experiencetraining RL policies, ideally for robotics or continuous control.
• Comfort with aphysics simulator: MuJoCo, Isaac Sim / Lab, Brax, Genesis, or similar.
• Willingness to work withreal hardware— robotics is an empirical science, and debugging a policy on real robot is part of the job.
• Sim‑to‑real transfer, domain randomization, or system identification.
• Dexterous manipulation, contact‑rich control, or tendon‑driven systems.
• Published work at ICRA, IROS, CoRL, RSS, ICML, NeurIPS, CVPR, ECCV, ICCV, or similar.

What We Offer

You'll be contributing to an open research problem with direct impact on the robot we're building at Clone, on a path to realize the most human‑like and human‑level android in the world.

• End‑to‑end ownership. From simulation to real hardware deployment — you'll own the full stack for your track, not just the training loop.
• Hardware access. Direct access to muscle‑driven robotic hands and the full sensor stack — not a simulation‑only role.
• Mountain View lab. On‑site in the Bay Area, alongside the core Intelligence & Behavior and Demos teams.
• Compute. The GPU resources to train the policies the work actually requires.
• Project guidance. Close collaboration with researchers who care about sim‑to‑real, musculoskeletal systems, and getting things to work on real hardware.
• Scaling. Our company is constantly growing. You will become part of an international team with wide development opportunities.
• 3‑month internship (including 8 days of paid holidays) with the possibility to extend to a full‑time job.

Recruitment Process

• CV and portfolio review
• On‑site task (technical, office in Mountain View, CA)