Computer Vision Research Engineer

Computer Vision Research Engineer | VLMs, Video Understanding & Multimodal AI | San Francisco, CA

I'm partnering with a well-funded frontier AI research startup developing low-latency multimodal models and intelligent agents capable of interacting with humans in real time.

They're looking for an experienced Computer Vision Research Engineer to develop advanced visual perception systems, initially focused on gaming environments, with future applications in robotics and human-AI collaboration.

The role:

• Research and develop video understanding models, VLMs and multimodal architectures
• Build real-time perception systems for recognising actions, objects and spatial relationships
• Develop temporal representations for understanding events across extended interactions
• Train and evaluate models using demonstrations, synthetic data and interactive environments
• Optimise visual models for low-latency inference and real-time interaction

What they're looking for:

• PhD in Computer Vision, Machine Learning or a related field
• Strong publications at CVPR, ICCV, ECCV, NeurIPS, ICLR or ICML
• Deep experience with VLMs, video understanding or multimodal transformers
• Strong Python/PyTorch research engineering experience
• Familiarity with recent VLM/VLA research and real-time visual perception

Why consider it?

• An opportunity to conduct original research within a well-backed AI lab, developing multimodal systems that bridge gaming, intelligent agents and robotics.
• You'll work on challenging research problems with direct applications to real-time human-AI interaction.

Location: San Francisco, CA (City)

Interested in learning more? Apply directly or send me a message for a confidential discussion.