Vision-Based Proficiency Research Intern — Multimodal Data

Honda Research Institute USA; San Jose (CA); On-site; USD 15,000 - 25,000; Part time

Job summary

Honda Research Institute USA in San Jose, CA seeks a Research Intern to develop vision-based models for assessing human proficiency and skill via force estimation. You will design data collection protocols, build multimodal capture setups, and create baselines using egocentric and exocentric video streams with force data.

The role emphasizes hands-on data collection and evaluation of vision-based approaches, with potential for publications.

Qualifications

• Currently enrolled in an MS or PhD program in Robotics, Computer Vision, Machine Learning, AI, or a closely related field.
• Hands-on experience building or operating multimodal data collection setups with calibration and time synchronization across streams.
• Strong programming skills in Python with PyTorch and writing clean, reproducible code.
• Comfort with hardware-in-the-loop debugging: device SDKs, drivers, serial/USB interfaces, data logging, and end-to-end troubleshooting of recording pipelines.
• Willingness to participate directly in data collection and in recording sessions with participants.
• Ability to drive a project from data collection protocol design through dataset capture to baseline models and evaluation.
• Strong written and verbal communication skills.

Responsibilities

• Design the data collection protocol and determine task variations to span proficiency levels.
• Build and validate capture setup (egocentric glasses, force sensors) and data pipelines.
• Synchronize egocentric streams with exocentric views and force measurements.
• Conduct data collection sessions with participants and/or researchers.
• Develop vision-based baselines for force estimation and evaluate against ground-truth forces.
• Design and validate metrics to capture task proficiency from signals.
• Optionally contribute to publications and dataset releases.

Skills

Python

PyTorch

Multimodal data collection

Sensor calibration

Time synchronization

Strong communication

Project management

Education

MS or PhD in Robotics, Computer Vision, ML or related field

Tools

Device SDKs

Job description

Honda Research Institute USA in San Jose, CA seeks a Research Intern to develop vision-based models for assessing human proficiency and skill via force estimation. You will design data collection protocols, build multimodal capture setups, and create baselines using egocentric and exocentric video streams with force data.

The role emphasizes hands-on data collection and evaluation of vision-based approaches, with potential for publications.