Binance Accelerator Program - Data Scientist (Reinforcement Learning, SFT, LLM Training)

Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. We are trusted by 300+ million people in 100+ countries for our industry-leading security, user fund transparency, trading engine speed, deep liquidity, and an unmatched portfolio of digital-asset products. Binance offerings range from trading and finance to education, research, payments, institutional services, Web3 features, and more. We leverage the power of digital assets and blockchain to build an inclusive financial ecosystem to advance the freedom of money and improve financial access for people around the world.

About Binance Accelerator Program Binance Accelerator Program is a concise fixed-term program designed for Early Career Talent to have an immersive experience in the rapidly expanding Web3 space. You will be given the opportunity to experience life at Binance and understand what goes on behind the scenes of the worlds’ leading blockchain ecosystem. Alongside your job, there will also be a focus on networking and development, which will expand your professional network and build transferable skills to propel you forward in your career. Learn about BAP Program HERE   Who may apply  Current university students and recent graduates

Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. We are trusted by 300+ million people in 100+ countries for our industry-leading security, user fund transparency, trading engine speed, deep liquidity, and an unmatched portfolio of digital-asset products. Binance offerings range from trading and finance to education, research, payments, institutional services, Web3 features, and more. We leverage the power of digital assets and blockchain to build an inclusive financial ecosystem to advance the freedom of money and improve financial access for people around the world. Who may apply Current University students and recent Graduates, who can commit 5 days per week (Monday -Friday) for 6 months tenure.

Responsibilities: Leveraging knowledge of large-scale models and intelligent agents, participate in the design and development of a series of AI-powered financial trading agency skills based on Web3 data, and integrate them into practical systems. Perform post-training of large-scale language models (SFT, RL, etc.) to enhance the model's ability to utilize Binance's internal trading skills. Assist in building and maintaining benchmark datasets to evaluate the performance of AI systems, and assist in building and iterating workflow prototypes for financial AI agent systems. Work closely with senior engineers to complete system design, integration, and deployment. Requirements: Currently pursuing or holding a Bachelor’s, Master’s, or Ph.D. degree in Computer Science, Artificial Intelligence, Financial Engineering, Automation, or a related field. Hands-on experience with post-training techniques such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RLHF / RLAIF) . Familiar with common fine-tuning and reinforcement learning frameworks, such as Llama Factory, Slime, Verl, and OpenRLHF. Familiarity with at least one mainstream deep learning framework (PyTorch, TensorFlow) and common LLM training/evaluation toolkits (Hugging Face Transformers, DeepSpeed, vLLM, etc.). Excellent communication skills and a strong willingness to learn quickly. Able to commit at least 6 months, working 5 days a week.