Build and continuously refine evaluations for multimodal and agentic frontier AI models across pretraining and post-training Build robust, reusable evaluation pipelines that scale across multiple model lines and product areas Produce auditable technical artifacts, including evaluation reports and model cards, at high reliability and speed Scope and deliver end-to-end evaluations under ambiguous and rapidly shifting requirements, re-prioritizing as the threat landscape and Meta's frontier models evolve Work across research, engineering, policy, and legal teams to align evaluation priorities with launch timelinesBachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience 1+ years of experience in ML engineering, LLM research, or a related technical role Background in one or multiple of privacy-preserving LLM development, memorization, pretraining data curation and post-training alignment Proficiency in Python and experience with machine learning frameworks Experience scoping, designing, and delivering medium-to-large technical projects with minimal direction, defining milestones and coordinating dependencies Proven experience in software engineering practices, including version control, testing, and code review practices Experience working with large-scale distributed systems and data pipelines Experience in implementing or developing benchmarks for large language models and multimodal models (e.g., vision-language, audio, video, browser agents) Experience in red-teaming AI systems, adversarial machine learning, or abuse prevention systems Publications at peer-reviewed venues (NeurIPS, ICML, ICLR, ACL, EMNLP, or similar) related to language model evaluation, AI safety, or deep learning PhD or Master's degree in Computer Science or relevant technical field, or equivalent practical experience with a focus on privacy and/or safety domainsMeta builds technologies that help people connect, find communities, and grow businesses. As a Research Engineer on this team, you will work alongside AI researchers to develop new evaluations grounded in real-world threat models, maintain existing evaluations so they remain current and reliable, and produce written artifacts that Meta can trust during high-stakes launches.