Binance Accelerator Program (Top Talent Program) – Data Scientist (AI Risk & Fraud Detection)

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, and more. Our mission is to increase the freedom of money and financial access for people around the world.

About the Programme

The Binance Accelerator Program is a highly selective internship for exceptional students. It is built like a traditional internship, but the selection bar is much higher. Accelerators work on real production problems with real impact, not side projects, and are mentored by senior data scientists and risk experts.

Role Overview

As the digital-asset industry continues to evolve, so does the risk landscape across the ecosystem. To stay ahead, Binance Risk is investing heavily in AI-driven risk management and fraud detection, so that we can proactively identify and address emerging risks and keep our users safe.

You will join the Risk AI team, working where AI technology meets real-world risk control. We are looking for interns who bring fresh perspectives and innovative approaches to identifying potential vulnerabilities, detecting unusual activities, enhancing risk monitoring and developing more proactive risk control mechanisms. You will apply machine learning, large language models (LLMs), agents and advanced data analytics to fraud detection and risk monitoring, and help turn new ideas into smarter, more efficient and scalable risk control solutions.

Responsibilities

• Research, design and build ML/AI models to detect fraud and abnormal behaviour across the platform. Examples include account takeover, identity and KYC fraud, payment and deposit/withdrawal fraud, market abuse and abnormal trading, and coordinated or syndicated attacks.
• Analyse large-scale transactional, behavioural, device and on-chain data to find emerging attack patterns, potential vulnerabilities and gaps in existing controls.
• Explore how LLMs, agents, graph learning and anomaly detection can be used in risk scenarios, such as automated investigation, alert triage, risk reasoning and real-time monitoring.
• Build fast prototypes (PoCs) to test new detection ideas, run rigorous offline and shadow evaluations, and deliver reproducible results.
• Help move validated prototypes into production risk models, rules and monitoring tools, working with risk operations, engineering and security teams.
• Track the latest research and industry incidents in AI, fraud detection and Web3 security, and turn the lessons into concrete, proactive risk control improvements.

Requirements

• Currently enrolled in a Master's or PhD programme at a QS World University Rankings Top 50 university.
• Majoring in Computer Science, Artificial Intelligence, Machine Learning, Statistics, Mathematics, Data Science, Financial Engineering or a closely related field.
• Relevant hands-on experience in AI/ML, data analytics or risk management, through prior internships, work experience, research projects or competitions.
• Strong foundations in machine learning and statistics, such as classification, anomaly detection, imbalanced learning, graph methods and model evaluation.
• Strong passion for AI and a solid understanding of modern AI technologies such as LLMs, agents and deep learning, including their strengths and limitations. Hands-on experience applying AI to real problems, and an AI-native way of working that makes active use of AI tools in daily research and development.
• Genuine interest in Web3 and the crypto industry, shown through projects, coursework, community involvement or personal use. Basic understanding of blockchain, exchanges or DeFi.
• Excellent problem-solving skills, analytical rigour and the ability to work on ambiguous, adversarial problems where attackers keep adapting.
• Strong communication and documentation skills. Able to explain technical findings clearly to both technical and non-technical stakeholders.

Bonus

• Prior experience in fraud detection, anti-money laundering (AML), credit risk, cybersecurity or trust & safety, at a fintech, bank, payments company, exchange or large internet platform.
• Hands-on experience with LLM techniques such as agent harness engineering and fine-tuning (e.g. SFT).
• On-chain data analysis experience (e.g. address clustering, fund-flow tracing, smart-contract risk) or familiarity with Web3 security incidents and attack vectors.
• Papers at top-tier conferences (NeurIPS, ICML, ICLR, KDD, WWW, CCS, USENIX Security, etc.), strong Kaggle or competition results, or notable open-source contributions.
• Hackathon or personal project experience in AI × Risk or AI × Crypto.

Why Binance

• Shape the future of finance 
• Collaborate with world-class talent in a user-centric global organization with a flat structure
• Tackle challenging projects in a fast-paced and innovative enviornment with autonomy
• Thrive in a results-driven workplace with opportunities for career growth and continuous learning
• Competitive salary and company benefits
• Remote-first, work-from-home arrangement (may vary depending on the nature of the role and team)

Binance is committed to being an equal opportunity employer. We believe that having a diverse workforce is fundamental to our success.

By submitting a job application, you acknowledge that you have read our Candidate Privacy Notice.

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.