Your personal AI career agent
.AI Research Engineer - RL Manipulation(m/w/x)
Developing RL algorithms for humanoid robot manipulation, closing sim-to-real gaps. MSc or PhD in Robotics/ML with RL and manipulation focus required. Energetic, collaborative team environment.
Requirements
- MSc or PhD in Robotics, Machine Learning, or related field
- Strong focus on reinforcement learning and manipulation
- Experience with robot manipulation problems
- Experience with contact-rich or dexterous tasks
- Strong background in reinforcement learning
- Experience with modern reinforcement learning algorithms
- Awareness of practical limitations of reinforcement learning
- Hands-on experience with sim-to-real transfer
- Excellent programming skills in Python
- Ability to operate independently
- Ability to push open-ended problems to completion
Tasks
- Develop new algorithms for RL-based manipulation
- Scale training systems for efficient learning
- Close the loop between simulation and real-world performance
- Tackle sparse rewards and exploration challenges
- Improve sim-to-real transfer through better modeling
- Enhance training strategies and use real-world data
- Design learning-based approaches for complex tasks
- Focus on dexterous and contact-rich interactions
- Target real-world humanoid capabilities
- Solve multi-stage manipulation problems with delayed rewards
- Address credit assignment and stability challenges
- Develop methods for reliable policy transfer
- Improve robustness and handle model mismatch
- Leverage domain randomization and system identification
- Optimize large-scale training pipelines
- Increase simulation throughput for complex behaviors
- Explore novel learning methods
- Integrate reinforcement learning with imitation learning
- Collaborate with simulation and control teams
- Ensure tight integration between algorithms and infrastructure
Work Experience
- approx. 1 - 4 years
Education
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- Python
- Robotics
- Machine Learning
- Reinforcement Learning
Benefits
Competitive Pay
- Competitive compensation package
Informal Culture
- Energetic, collaborative team
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
Not a perfect match?
- Flexion RoboticsFull-timeOn-siteSeniorZürich
- Flexion Robotics
.AI Engineer - Dexterous Manipulation(m/w/x)
Full-timeOn-siteExperiencedZürich - Flexion Robotics
Robotics Engineer - Modeling & Sim-to-Real Transfer(m/w/x)
Full-timeOn-siteExperiencedZürich - Intrinsic
Research Scientist, Deep Learning(m/w/x)
Full-timeOn-siteExperiencedZürich - Flexion Robotics
Internship - Robotics Manipulation(m/w/x)
Full-timeInternshipOn-siteZürich
.AI Research Engineer - RL Manipulation(m/w/x)
Developing RL algorithms for humanoid robot manipulation, closing sim-to-real gaps. MSc or PhD in Robotics/ML with RL and manipulation focus required. Energetic, collaborative team environment.
Requirements
- MSc or PhD in Robotics, Machine Learning, or related field
- Strong focus on reinforcement learning and manipulation
- Experience with robot manipulation problems
- Experience with contact-rich or dexterous tasks
- Strong background in reinforcement learning
- Experience with modern reinforcement learning algorithms
- Awareness of practical limitations of reinforcement learning
- Hands-on experience with sim-to-real transfer
- Excellent programming skills in Python
- Ability to operate independently
- Ability to push open-ended problems to completion
Tasks
- Develop new algorithms for RL-based manipulation
- Scale training systems for efficient learning
- Close the loop between simulation and real-world performance
- Tackle sparse rewards and exploration challenges
- Improve sim-to-real transfer through better modeling
- Enhance training strategies and use real-world data
- Design learning-based approaches for complex tasks
- Focus on dexterous and contact-rich interactions
- Target real-world humanoid capabilities
- Solve multi-stage manipulation problems with delayed rewards
- Address credit assignment and stability challenges
- Develop methods for reliable policy transfer
- Improve robustness and handle model mismatch
- Leverage domain randomization and system identification
- Optimize large-scale training pipelines
- Increase simulation throughput for complex behaviors
- Explore novel learning methods
- Integrate reinforcement learning with imitation learning
- Collaborate with simulation and control teams
- Ensure tight integration between algorithms and infrastructure
Work Experience
- approx. 1 - 4 years
Education
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- Python
- Robotics
- Machine Learning
- Reinforcement Learning
Benefits
Competitive Pay
- Competitive compensation package
Informal Culture
- Energetic, collaborative team
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
About the Company
Flexion Robotics
Industry
IT
Description
Flexion builds the intelligence layer for next-gen humanoid robots, accelerating their real-world deployment.
Not a perfect match?
- Flexion Robotics
Research Engineer - Dexterous Manipulation (Egocentric Models)(m/w/x)
Full-timeOn-siteSeniorZürich - Flexion Robotics
.AI Engineer - Dexterous Manipulation(m/w/x)
Full-timeOn-siteExperiencedZürich - Flexion Robotics
Robotics Engineer - Modeling & Sim-to-Real Transfer(m/w/x)
Full-timeOn-siteExperiencedZürich - Intrinsic
Research Scientist, Deep Learning(m/w/x)
Full-timeOn-siteExperiencedZürich - Flexion Robotics
Internship - Robotics Manipulation(m/w/x)
Full-timeInternshipOn-siteZürich