Robotics AI Research Engineer — Multimodal Manipulation

Flexion Robotics; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Competitive compensation

Relocation sponsorship

401(k) with company contributions

Health, dental & vision insurance

Open PTO policy

Job summary

Flexion Robotics is seeking an experienced Research Scientist/Engineer to advance foundation models for dexterous manipulation in real-world robotics. You will drive large-scale experiments and build systems translating research into robust robot behavior.

The role requires a PhD or equivalent, expertise in multimodal models, RL/IL, and vision-language data. You will work across hardware and software teams to push capabilities in simulated and real environments in San Francisco.

Qualifications

• PhD in Computer Science, a related field, or equivalent practical experience.
• Experience with vision, vision-language, video, and other multimodal models, especially ones trained with human data.
• Experience with multimodal generative modeling, training, and inference.
• Experience with reinforcement learning and imitation learning.

Responsibilities

• Scalable data integration from human video demonstrations and wearable systems into foundation model workflows.
• Reconstruct 3D objects and environments from capture data for simulation-based scenario synthesis.
• Develop simulation-to-real and RL pipelines to produce dexterous manipulation policies.
• Design, train, and evaluate robot foundation models translating multi-sensor data into robust control.
• Advance embodied transfer between human action data and high-DOF robotic hands and humanoid platforms.

Skills

Vision models

Multimodal models

RL & IL

Dataset design

Robotics platforms

Education

PhD in CS or related field

Tools

Simulators

Robotics hardware

Job description

Flexion Robotics is seeking an experienced Research Scientist/Engineer to advance foundation models for dexterous manipulation in real-world robotics. You will drive large-scale experiments and build systems translating research into robust robot behavior.

The role requires a PhD or equivalent, expertise in multimodal models, RL/IL, and vision-language data. You will work across hardware and software teams to push capabilities in simulated and real environments in San Francisco.