VLM Researcher

Nori Robotics (YC S26) builds affordable humanoid robots. Our work connects some of the world's most novel multimodal, creative, and behavioral datasets to robots and consumer applications used by real customers. We're looking for hungry, talented, curious people to join our team.

Scope: Own the research and model training that let robots interpret their surroundings and respond appropriately. Learn structured representations of people, events, space, and ongoing interactions from video, audio, and sensor observations.

What you will work on

• Develop and fine-tune vision-language models for temporal understanding, spatial grounding, and human interaction.

• Define learning objectives, dataset specifications, and experiments with the multimodal engineer, who owns data preparation and QA/QC.

• Evaluate scene understanding, hallucinations, temporal consistency, and response relevance on held-out data and real-world sessions.

• Work with the LLM researcher and harness engineer to bring structured observations and model responses into robots and products.

Requirements

• Research experience training vision-language or video models, with strong Python and PyTorch or JAX and practical distributed-training experience.

• Demonstrated work in temporal or spatial grounding, with reproducible experiments and rigorous evaluation of model failures and generalization.

• Nice to have: streaming video understanding, cross-modal fusion, embodied perception, or relevant publications.

San Francisco, CA. Full time. In person.

Compensation. Base pay: $150,000-$250,000 per year. Base pay varies with job-related knowledge, skills, and experience.