Research Scientist, Multi-Modal Human Understanding

Meta; Pittsburgh, Burlingame (Allegheny County, CA); On-site; USD 150,000 - 190,000; Full time

Job summary

Meta seeks a Research Scientist to advance multi-modal AI technologies for human understanding and synthesis. You will develop Vision-Language Models (VLMs) and video foundation models that enable machines to perceive, interpret, and generate rich representations of human behavior and interaction.

Requirements include a Bachelor's degree in a technical field with 2+ years in multi-modal AI, PyTorch experience, and a track record of research contributions at major venues.

Qualifications

• Candidate has a BS or higher in a technical field before joining Meta.
• 2+ years in multi-modal AI research with VLMs, video or human-centric AI.
• Experience training large-scale neural networks and transformers.
• Proven ability to design experiments and analyze multi-modal benchmarks.
• Proficient in Python for research or production code.
• Publication track record in CVPR/ICCV/NeurIPS is valued.

Responsibilities

• Develop Vision-Language Models and video foundation models for understanding and generation.
• Advance multi-modal AI research spanning vision, language, and video.
• Implement and train large-scale neural networks using PyTorch.
• Design experiments to evaluate model performance across modalities.
• Contribute to publications and disseminate research findings.

Skills

Multimodal AI

Vision-Language Models

Video Understanding

Transformers

Python

Research Experience

Scientific Publications

Education

Bachelor's degree in Computer Science / Computer Engineering or related field

Tools

PyTorch

Job description

Meta is seeking a Research Scientist to advance multi-modal AI technologies for human understanding and synthesis. In this role, you will develop Vision-Language Models (VLMs) and video foundation models that enable machines to perceive, interpret, and generate rich representations of human behavior, expression, and interaction. Your research will span multi-modal reasoning, video understanding, and generative synthesis, enabling more natural and intuitive human-computer interaction at scale.

Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta

• 2+ years of experience in multi-modal AI research, including hands-on work with Vision-Language Models, video understanding, or human-centric AI systems
• 2+ years of experience implementing and training large-scale neural networks using frameworks such as PyTorch, with experience on transformer-based architectures
• Experience designing and executing experiments to evaluate multi-modal model performance, including quantitative analysis across vision, language, and video benchmarks
• Experience writing production-quality or research-quality code in Python for multi-modal AI applications
• Experience developing or fine-tuning Vision-Language Models for human understanding tasks
• Experience with video foundation models, temporal transformers, or large-scale video pretraining
• Track record of contributing to published multi-modal AI research at venues such as CVPR, ICCV, or NeurIPS
• Experience with generative models for human synthesis including diffusion models, GANs, or autoregressive models for video or motion generation