Meta is seeking an AI Research Scientist specializing in vision large language models (VLLM) to lead and collaborate on research that advances the state of the art in multimodal reasoning and generation. The role involves working towards long-term ambitious research goals while identifying intermediate milestones. The candidate will directly contribute to experiments, including designing experimental details, writing reusable code, running evaluations, and organizing results. The position requires collaboration with a large team, contributions to publications and open-sourcing efforts, and mentoring other team members. The research conducted will prioritize applications that can be integrated into Meta's product development.