Sim2Real Robotics Research Scientist

Robotics and AI Institute

Cambridge (MA)

On-site

USD 141,000 - 326,000

Full time

5 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Annual bonus
Medical benefits
Commuter cost subsidy

Job summary

Robotics and AI Institute in Cambridge, MA is seeking a Sim2Real Research Scientist to advance policies on our novel hardware for dexterous manipulation. You will collaborate with researchers and engineers to deploy, test, and refine RL policies directly on hardware, while reducing the sim-to-real gap and enabling high-throughput experiments.

The role requires deep RL expertise, multi-modal sensing, and strong Python skills, with experience in simulators like MuJoCo and PhysX.

Qualifications

  • M.S. or Ph.D. in Robotics, Computer Science, Machine Learning, or a related field.
  • Hands-on expertise with real-world robot integration, hardware deployment, physical testing setups.
  • Experience in developing, adapting, fine-tuning, or deploying multi-modal policies integrating vision and contact-rich physical modalities (tactile or force/torque sensing).
  • Solid background in deep reinforcement learning (RL) algorithms, modern simulation-to-real (Sim2Real) transfer methodologies, reward engineering/shaping, and curriculum design.
  • Experience in incorporating state-of-the-art workflows and techniques to automate robotics training loops, simulation environments, or Sim2Real transfer tuning.
  • Demonstrated experience in Sim2Real techniques for either manipulation or locomotion is required, with explicit investigation and application for dexterous, contact-rich manipulation preferred.
  • Proficiency in Python, deep learning frameworks, and physics simulation engines (e.g., PhysX, MuJoCo, Netwon) applied to complex robotic systems.

Responsibilities

  • Develop, deploy, test, and debug reinforcement learning (RL) policies on real-world novel robotic hardware platforms for dexterous manipulation tasks.
  • Investigate, analyze, and mitigate domain gaps between physics simulation and real-world execution for contact-rich manipulation through parameter identification, dynamic domain randomization, and real2sim alignment to improve simulator fidelity.
  • Design and implement curriculum training frameworks, demonstration-led state guidance, and reward engineering strategies to overcome exploration bottlenecks in tight-tolerance manipulation tasks.
  • Integrate multi-modal sensor inputs—including vision, tactile/contact sensing, 6-axis force/torque, and joint proprioception—into real-time sensorimotor learning architectures and policies.
  • Explore policy learning techniques for highly-dynamic, contact-rich action spaces regulating speeds, impedances, and energy expenditure.
  • Develop high-throughput experimental workflows and collaborate with research scientists, hardware engineers, and control teams to co-design closed-loop learning systems and maintain technical documentation.

Skills

Reinforcement Learning
Sim2Real
Dexterous manipulation
Python
Robotics systems
Multi-modal sensing

Education

M.S. or Ph.D. in Robotics, Computer Science, Machine Learning, or related field

Tools

IsaacLab
MuJoCo
PhysX
Newton/Physics engines

Job description

Our Mission

Our mission is to solve the most important and fundamental challenges in AI and Robotics, enabling future generations of intelligent machines that will help us all live better lives.

The RAI Dexterous Manipulation team is developing advanced manipulation systems capable of performing precise, contact-rich tasks at or above human cadence. By co-designing hardware, software, controls, and machine learning components in an integrated fashion, we seek to push the state of the art to enable reliable, high-performance skills across complex manufacturing and construction tasks capable of real-world deployment.

Responsibilities

We are seeking a highly qualified Sim2Real Research Scientist to support the development, deployment, and testing of policies on our novel hardware system. In this role, you will be responsible for working closely with researchers and engineers exploring high-fidelity simulation-based Reinforcement Learning (RL) methods specifically for dexterous manipulation. Key responsibilities will be developing, testing, and debugging learned policies on the hardware, investigating how to close the gap between simulation and real world systems, and developing suitable testing techniques to facilitate high-throughput experimental work.

Candidates may hold a M.S. or Ph.D. in Robotics, Computer Science, Machine Learning, or a closely related quantitative field, with real-world robot integration and development expertise. Knowledge of deep reinforcement learning, multimodal visual-force-tactile state estimation, and sim2real learning techniques are also desirable. Direct experience with NVIDIA’s IsaacLab experimental framework and applying RL techniques to dexterous robotic manipulation is strongly preferred; however, candidates with demonstrated expertise in sim2real RL for locomotion and whole-body loco-manipulation are also highly encouraged to apply.

  • Develop, deploy, test, and debug reinforcement learning (RL) policies on real-world novel robotic hardware platforms for dexterous manipulation tasks.
  • Investigate, analyze, and mitigate domain gaps between physics simulation and real-world execution for contact-rich manipulation through parameter identification, dynamic domain randomization, and real2sim alignment to continuously improve simulator fidelity.
  • Design and implement curriculum training frameworks, demonstration-led state guidance, and reward engineering strategies to overcome exploration bottlenecks in tight-tolerance manipulation tasks.
  • Integrate multi-modal sensor inputs—including vision, tactile/contact sensing, 6-axis force/torque, and joint proprioception—into real-time sensorimotor learning architectures and policies.
  • Explore policy learning techniques for highly-dynamic, contact-rich action spaces capable of regulating speeds, impedances, and energy expenditure.
  • Develop high-throughput experimental workflows and collaborate closely with research scientists, hardware engineers, and control teams to co-design closed-loop learning systems and maintain technical documentation.
Requirements
  • M.S. or Ph.D. in Robotics, Computer Science, Machine Learning, or a related field.
  • Hands‑on expertise with real-world robot integration, hardware deployment, physical testing setups.
  • Experience in developing, adapting, fine‑tuning, or deploying multi‑modal policies integrating vision and contact‑rich physical modalities (tactile or force/torque sensing).
  • Solid background in deep reinforcement learning (RL) algorithms, modern simulation‑to‑real (Sim2Real) transfer methodologies, reward engineering/shaping, and curriculum design.
  • Experience in incorporating state‑of‑the‑art workflows and techniques to automate robotics training loops, simulation environments, or Sim2Real transfer tuning.
  • Demonstrated experience in Sim2Real techniques for either manipulation or locomotion is required, with explicit investigation and application of these methods to dexterous, contact‑rich robotic manipulation considered a preference.
  • Proficiency in Python, deep learning frameworks, and physics simulation engines (e.g., Physx, MuJoCo, Netwon) applied to complex robotic systems.

$140,910 - $326,040 a year

The current reasonable and good faith estimate of the annual base salary range for this position is $140,910 - $326,040, which is based on a number of factors including, but not limited to, relevant skills and experience, educational background and certifications, performance and qualifications, market demand for the role, geographic location, and other organizational needs. An individual candidate may be considered for this position at a different job level, in which case the appropriate salary range will be provided to the candidate after their qualifications have been established. Employees who are new to the RAI Institute typically receive an offer that is between the minimum and the midpoint of the posted salary range to allow for growth within the range over time.

Base pay is part of a competitive total compensation package that may include an annual bonus, a long‑term cash incentive, monthly cell phone cost reimbursement, commuter cost subsidy, medical benefits, and more. Any final job offer will be determined based on our established compensation range for the role, the candidate’s experience and qualifications, internal parity, and market and business considerations. The advertised pay range is not a guarantee or promise of a specific wage.

We provide equal employment opportunities to all employees and applicants for employment and prohibit discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Software and Controls Team Lead
Software and Controls Team Lead

Robotics and AI Institute • Cambridge (MA)

On-site
USD 200,000 - 372,000
Sr. Simulation Engineer
Sr. Simulation Engineer

Robotics and AI Institute • Cambridge (MA)

On-site
USD 176,000 - 372,000
Docker
Cloud computing
Distributed systems
+3
Senior Software Engineer Interactive Mobility
Senior Software Engineer Interactive Mobility

Robotics and AI Institute • Cambridge (MA)

On-site
USD 176,000 - 326,000
Robotics Software Engineer Interactive Mobility
Robotics Software Engineer Interactive Mobility

Robotics and AI Institute • Cambridge (MA)

On-site
USD 141,000 - 261,000
Applied Scientist II - Robotics Simulation, Amazon Robotics R&D
Applied Scientist II - Robotics Simulation, Amazon Robotics R&D

Amazon Inc. • Town of Westboro (WI)

On-site
USD 143,000 - 193,000
Applied Scientist II - Robotics Simulation, Amazon Robotics R&D
Applied Scientist II - Robotics Simulation, Amazon Robotics R&D

Amazon Inc. • Sunnyvale (CA)

Hybrid
USD 142,800 - 193,200
Research Engineer, Robotics: Physics Simulation and Sim-to-Real
Research Engineer, Robotics: Physics Simulation and Sim-to-Real

Ai2 • Seattle (WA)

On-site
USD 118,800 - 178,200
Medical, dental, and vision insurance
401k plan
Bonus opportunities
+2
Sim2Real Robotics Scientist: Dexterous Manipulation & RL
Sim2Real Robotics Scientist: Dexterous Manipulation & RL

Robotics and AI Institute • Cambridge (MA)

On-site
USD 141,000 - 326,000
Annual bonus
Medical benefits
Commuter cost subsidy
Hardware Integration and Test Engineer
Hardware Integration and Test Engineer

Robotics and AI Institute • Cambridge (MA)

On-site
USD 126,000 - 289,000
Motor dynamometer experience
Rust for embedded bring-up (bonus)
System identification (bonus)
+2
Research Engineer, Robotics - Roboticist
Research Engineer, Robotics - Roboticist

The Allen Institute for Artificial Intelligence • Seattle (WA)

On-site
USD 129,000 - 193,000
Medical insurance
Dental and vision coverage
Retirement plan
+1