Robotics AI Research Engineer - Multimodal & RL

Flexion; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Competitive compensation

Enhanced pension plan

Relocation & permit sponsorship

Central Zürich office with top-tierRob

Joining Europe's leading robotics team

Energetic, collaborative culture witha

Job summary

Flexion in San Francisco seeks a Research Scientist/Engineer to advance generalizable manipulation using video demonstrations, wearable data, and multimodal models.

You will own end-to-end experimentation, build scalable capture pipelines, and translate cutting-edge research into robust, real-world robotic systems. PhD required; strong ML, RL/Imitation, and simulators experience preferred.

Qualifications

• PhD or equivalent practical experience in CS or related field.
• Experience with vision, vision-language, video, and other multimodal models.
• Experience with multimodal generative modeling, training, and inference.
• Experience with reinforcement learning and imitation learning.

Responsibilities

• Scalable Human Data Integration: develop pipelines to integrate video demonstrations and wearable data into foundation model and RL workflows.
• 3D Object & Interaction Reconstruction: build pipelines to reconstruct manipulated 3D objects and environments from capture data.
• Simulation-to-Real & Reinforcement Learning: build simulation environments with reconstructed assets for dexterous manipulation policies.
• Multimodal Policy Architecture & Evaluation: design and evaluate models translating multi-sensor data into robust control.
• Embodied Transfer: design algorithms bridging human embodiment to dexterous robot hands and humanoid platforms.

Skills

Vision and multimodal models

Reinforcement learning

Imitation learning

Dataset design

Capture methodologies

Robotics simulators

Education

PhD in Computer Science or related field

Tools

Robotics simulators

Job description

Flexion in San Francisco seeks a Research Scientist/Engineer to advance generalizable manipulation using video demonstrations, wearable data, and multimodal models.

You will own end-to-end experimentation, build scalable capture pipelines, and translate cutting-edge research into robust, real-world robotic systems. PhD required; strong ML, RL/Imitation, and simulators experience preferred.