Research Scientist role focused on designing and developing novel benchmarks and evaluation methodologies for frontier AI capabilities within Meta Superintelligence Labs (MSL). The role involves measuring and understanding AI capabilities, influencing research direction, and collaborating with researchers and technical leadership. Requires a strong publication record and experience in machine learning research, particularly in evaluation and deep learning.

Research Scientist role focused on developing and implementing novel evaluations for frontier AI systems, shaping research direction and model development. Requires strong ML research background, experience with LLM/multimodal evaluation, and publication record.

Research Engineer role focused on building and curating benchmarks and evaluation environments for advanced AI models across text, vision, and audio. The role involves developing novel benchmarks, integrating existing ones, and creating scalable evaluation tooling to directly impact research direction and model development. Requires strong ML engineering and research skills, Python proficiency, experience with ML frameworks, and a track record of publications in relevant venues.

Research Scientist Manager to lead a team focused on measurement and evaluation of AI Assistants powered by foundation models. The role involves defining scientific strategy for evaluation, ensuring methodological rigor, and collaborating with product, engineering, and training teams to ensure reliability and trustworthiness at scale.