Embodied AI Research Engineer – Robotics & Multimodal

Flexion Robotics; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Competitive compensation

Enhanced pension plan

Enhanced holiday & paid leave perks

Relocation & permit sponsorship

Central Zürich office with top-tierRob

401(k) with company contributions

Health, dental & vision coverage

Job summary

Flexion Robotics is seeking an expert in robotics foundation models and multimodal human action data to advance dexterous manipulation. You will bridge human embodiment and robotic execution using video demonstrations and wearable capture systems while scaling data and models to robust, real-world deployments.

You will drive large-scale experiments, develop novel systems, and deploy ideas across core physical intelligence problems, turning cutting-edge research into practical robotic

Qualifications

• PhD or equivalent practical experience.
• Experience with vision-language and multimodal models.
• Experience with multimodal generative modeling, training, and inference.
• Experience with reinforcement learning and imitation learning.

Responsibilities

• Develop scalable data integration pipelines for human video demonstrations and wearable capture systems into foundation model and RL workflows.
• Build automated pipelines to reconstruct 3D objects and environments from capture data for simulation and digital twin assets.
• Create simulation environments with reconstructed assets and leverage RL, tactile and force feedback for dexterous manipulation policies.
• Design, train, and evaluate robot foundation models translating multi-sensor data streams into robust control.
• Develop algorithms to bridge human embodiment to dexterous robotic hands and humanoid platforms.

Skills

Multimodal understanding

Vision-language models

Reinforcement learning

Imitation learning

Data capture pipelines

Education

PhD in Computer Science or related field

Tools

VLA

WAM

Robotics simulators

Job description

Flexion Robotics is seeking an expert in robotics foundation models and multimodal human action data to advance dexterous manipulation. You will bridge human embodiment and robotic execution using video demonstrations and wearable capture systems while scaling data and models to robust, real-world deployments.

You will drive large-scale experiments, develop novel systems, and deploy ideas across core physical intelligence problems, turning cutting-edge research into practical robotic