Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. We are trusted by over 280 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.

REQUIREMENTS

• 2+ years of experience in machine learning or AI systems development.
• Strong background in LLMs, prompt engineering, and AI Agent frameworks (LangChain, LlamaIndex, CrewAI, AutoGen, etc.).
• Hands-on experience with RAG systems, vector databases, and real-time data integration.
• Proficiency in Python; familiarity with FastAPI, Celery, or Ray a plus.
• Experience with APIs (OpenAI, Anthropic) and LLM fine-tuning.
• Knowledge of big data tools (Spark, Kafka, Redis) and containerized environments (Docker, Kubernetes).
• AI Agent Specialization: Workflow design (planning, reasoning, tool use), guardrails and oversight frameworks, semantic search, monitoring, and rollback strategies.
• Background: Master’s degree (or equivalent experience) in Data Science, AI Engineering, or Applied ML. Experience with large-scale, real-time systems; financial or trading domain knowledge preferred.
• Soft Skills: Strong problem-solving and communication skills, ability to work in fast-changing 0 1 environments, and a passion for AI agents, LLMs, and intelligent automation.

ABOUT THE ROLE

We are building the next frontier of intelligent trading systems, leveraging AI Agents to autonomously handle complex workflows in fraud detection, customer support, risk monitoring, and operational decision-making. As a Data Scientist in AI Agent Engineering, you will design, build, and deploy production-grade multi-agent systems that reason, plan, and execute tasks at scale. You will work across agent orchestration, retrieval systems, safety guardrails, and MLOps to bring intelligent autonomy into our trading ecosystem.

RESPONSIBILITIES

• AI Agent Development & Orchestration: Design and implement multi-agent systems to manage fraud detection, risk monitoring, and operational workflows. Build middleware, task delegation, and communication protocols for seamless agent interaction.
• RAG & Knowledge Systems: Develop retrieval-augmented generation (RAG) pipelines integrating real-time market, regulatory, and trading data. Build and maintain vector databases and semantic search systems that power contextual agent decision-making.
• Safety & Governance: Implement safety frameworks, guardrails, and human-in-the-loop approval systems. Monitor agent behaviour, detect anomalies, and enforce regulatory and business compliance.
• Agent CI/CD & Infrastructure: Develop agent testing, versioning, and deployment pipelines. Build A/B testing frameworks, rollback strategies, and monitoring systems to optimise production agents.
• Collaboration: Work closely with risk, infrastructure, and product teams to embed safety constraints, streamline agent-human interaction patterns, and adapt agent solutions to business needs.