Data Scientist - CS Chatbot (SFT)

About the Company

Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. Binance offerings range from trading and finance to education, research, payments, institutional services and Web3 features. We leverage digital assets and blockchain to build an inclusive financial ecosystem.

About the Role

We are seeking a Data Scientist focused on advancing customer service scheduling optimization through AI, specifically developing and refining Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks tailored to customer service/chatbot scenarios.

Responsibilities

• Own the full LLM pipeline from data preparation to production real-case usage.
• Design, iterate and optimize prompts (zero-/few-shot, chain-of-thought, tool-calling, etc.) to maximize model utility and safety across products and languages.
• Build and maintain RAG QA/search systems that connect to multi-source knowledge bases.
• Deploy and operate LLM inference services (vLLM/SGLang) on multi-GPU or cluster environments and optimize inference/quantization.
• Design, implement and operate multi-agent LLM architectures (e.g. LangGraph, CrewAI, AutoGen) including task decomposition, agent orchestration, memory sharing and tool-calling workflows.
• Develop evaluation pipelines (automatic metrics & human feedback) to measure prompt and model quality, bias, and hallucination rates.
• Collaborate with product and customer service teams to integrate AI models into conversational chatbots across scenarios.
• Track cutting-edge research, author technical blogs, and continuously improve current architecture.

Qualifications

• Master’s degree or higher in Computer Science, Data Science or related field.
• 2+ years of deep-learning/NLP experience, including 1+ year practical LLM work (SFT, DPO, RAG, quantization, inference optimization, etc.).
• Demonstrated prompt engineering & tuning expertise (few-shot design, structured prompting, prefix-/p-tuning, reward re-ranking, safety filtering).
• Practical experience building and deploying multi-agent LLM workflows and understanding of agent-orchestrator patterns, shared memory, long-horizon planning and guard-rail design.
• Familiarity with multi-GPU/cluster deployment and inference architectures (vLLM/SGLang) and production operation of LLM services.
• Clean coding practices, strong English communication, self-driven ownership, and a passion for rapid learning and collaboration.

Skills

• Experience with SFT/DPO, RAG, quantization and inference optimization for LLMs.
• Ability to design prompt strategies, evaluation pipelines, and safety/bias mitigation.
• Experience integrating models into production conversational systems with product/CS stakeholders.

Benefits

• Shape the future with the world’s leading blockchain ecosystem and collaborate with world-class talent.
• Autonomy on fast-paced, innovative projects and opportunities for career growth and continuous learning.
• Competitive salary and company benefits.
• Work-from-home arrangement (the arrangement may vary depending on the business team).

Additional Information

• This role is stated as 100% remote / work from home based.
• Binance is an equal opportunity employer and values a diverse workforce.
• By applying you agree to Binance's Candidate Privacy Notice.
• Binance may use AI tools to support parts of the hiring process; final hiring decisions are made by humans.