M
AI Research Scientist, Post-Training - Meta Superintelligence Labs
Meta
Menlo Park, CA
≈ 999,8 тыс.–1,9 млн ₽ · 10,9 тыс.–21 тыс. €
12 500 – 24 083 $
🏢 Офис
Senior
Полная занятость
Продуктовая
Tech
Описание вакансии
Обязанности
•Collaborate with cross-functional research teams
•Curate post training datasets
•Define data quality frameworks
•Design post training data collection methodology
•Develop alignment strategies
•Generate synthetic data
•Improve model quality
•Lead technical research projects from conception to production
•Optimize post training recipes
•Research data for agentic behaviors
•Research data for expert domains
•Research post training recipes
Технологии: DPO, Data Curation, Data Generation, Data Quality, Data Quality Management, Deep learning, Human Feedback, Language Model, Language Processing, Language model training, Learning from Human Feedback, Machine Learning, Model Alignment, Model Training, Natural Language, Natural Language Processing, Quality management, Reinforcement Learning, Reinforcement Learning from Human Feedback, Research Methodology, Synthetic Data Generation, Synthetic data