Meta is seeking Research Scientists to join the Post-Training team within Meta Superintelligence Labs (MSL). High-quality data is the core of AI progress at MSL, fueling the complex capabilities we build, how our models reason, and how they interact with the world.
What you'll do
As a Research Scientist, you will provide the technical vision to design, generate, and curate the critical post-training data (SFT, RLHF) that aligns and enhances our frontier AI systems. You will conduct research to develop and optimize post-training recipes that directly improve model quality.
What you need
- Responsibility 1: Design novel methodologies for post-training data collection, curation, and synthetic data generation
- Responsibility 2: Define data quality frameworks and alignment strategies that guide capability development across MSL, particularly for complex reasoning and agentic behaviors
- Responsibility 3: Drive the scientific vision for eliciting high-quality data in expert domains (finance, legal, health, STEM) and complex agentic trajectories (Deep research, computer use, UI generation)
- Responsibility 4: Conduct research to develop and optimize post-training recipes that directly improve model quality
- Responsibility 5: Partner with cross-functional research teams across product and model training to identify and prioritize gaps in model capabilities
- Responsibility 6: Contribute to research workstreams that shape the long-term direction of data-centric AI at MSL, working independently while also contributing to team goals and organizational priorities
