Research Scientist - LLM Foundation Models
BinanceJob Location
Job Summary
The Research Scientist - LLM Foundation Models role at Binance involves enhancing reasoning and planning throughout the development process of foundation models. The candidate will synthesize large-scale data using methods such as rewriting, augmentation, and generation to improve model capabilities. They will also investigate and implement robust evaluation methodologies to assess model performance. Additionally, they will teach foundation models to use tools, interact with APIs, and code interpreters. The ideal candidate has research experience with RL, LLM, and large-scale model training, proficiency in data structures and fundamental algorithm skills, and excellent problem analysis and communication skills. Binance offers a fast-paced, mission-driven organization with opportunities for career growth and continuous learning.
Responsibilities
- Reasoning and planning for foundation models: Enhance reasoning and planning throughout the entire development process, including data acquisition, model evaluation, SFT, reward modeling, and reinforcement learning, to improve overall performance.
- Synthesize large-scale, high-quality data using methods such as rewriting, augmentation, and generation to improve the capabilities of foundation models in various stages (pretraining, SFT, RL).
- Solve complex tasks using system 2 thinking and leverage advanced decoding strategies such as MCTS, A*.
- Investigate and implement robust evaluation methodologies to assess model performance at various stages.
- Teach foundation models to use tools, interact with APIs, and code interpreters. Build agents and multi-agent systems to solve complex tasks.
Requirements
- Proficiency in research experience with RL, LLM, and familiarity with large-scale model training is preferred.
- Proficiency in data structures and fundamental algorithm skills, and fluency in Python or C++/Java.
- Experience with influential projects or papers in RL, NLP, or Deep Learning is preferred.
- Excellent problem analysis and problem-solving skills, capable of deeply addressing challenges in large-scale model training and application.
- Good communication and collaboration skills, with the ability to explore new technologies with the team and promote technological progress.
