Taro Logo

Algorithm Engineer, LLM (Safety First) – AI Safety

Leading global blockchain ecosystem behind the world's largest cryptocurrency exchange by trading volume and registered users.
Taipei City, TaiwanPhaya Thai, Bangkok 10400, ThailandBrisbane QLD, Australia
Machine Learning
Senior Software Engineer
Remote
5,000+ Employees
5+ years of experience
AI · Finance · Blockchain

Job Description

Binance, the world's largest cryptocurrency exchange serving over 280 million users across 100+ countries, is seeking an LLM Algorithm Engineer focused on AI Safety. This role is crucial for developing robust AI guardrails and safety frameworks for large language models and intelligent agents. The position combines cutting-edge AI development with practical applications in cryptocurrency and blockchain technology. The successful candidate will work on critical AI-powered products including Customer Support Chatbots, Compliance Systems, Search, and Token Reports.

The role demands expertise in AI safety, requiring the development of frameworks to prevent issues like prompt injection, hallucinations, and unsafe outputs. You'll be responsible for implementing privacy controls, building red-teaming pipelines, and ensuring compliance across all AI applications. This position offers a unique opportunity to work at the intersection of AI safety and blockchain technology, with the potential to impact millions of users globally.

Working at Binance means joining a dynamic, user-centric organization with a flat structure, where innovation and autonomy are encouraged. The company offers competitive compensation, flexible work arrangements, and significant opportunities for professional growth. This role is perfect for someone with strong technical skills in machine learning and AI safety who is passionate about cryptocurrency and Web3 technologies.

Last updated a day ago

Responsibilities For Algorithm Engineer, LLM (Safety First) – AI Safety

  • Design and build an AI Guardrails framework as a safety layer for LLMs and agent workflows
  • Define and enforce safety, security, and compliance policies across applications
  • Detect and mitigate prompt injection, jailbreaks, hallucinations, and unsafe outputs
  • Implement privacy and PII protection: redaction, obfuscation, minimisation, data residency controls
  • Build red-teaming pipelines, automated safety tests, and risk monitoring tools
  • Continuously improve guardrails to address new attack vectors, policies, and regulations
  • Fine-tune or optimise LLMs for trading, compliance, and Web3 tasks
  • Collaborate with Product, Compliance, Security, Data, and Support to ship safe features

Requirements For Algorithm Engineer, LLM (Safety First) – AI Safety

Python
Java
  • Master's/PhD in Machine Learning, AI, Computer Science, or related field
  • Research track record (ICLR, NeurIPS, ACL, ICML) a plus
  • Hands-on experience building LLM/agent guardrails
  • Practical experience with hallucination mitigation and safety evaluation
  • Proven ability to ship AI safety frameworks to production
  • Strong coding in Python (Java a plus); expertise in PyTorch/TensorFlow/JAX
  • Understanding of privacy, PII handling, data governance, and risk frameworks
  • Interest in crypto, Web3, and financial systems
  • Self-driven with strong ownership and delivery skills
  • Excellent communication and collaboration abilities

Benefits For Algorithm Engineer, LLM (Safety First) – AI Safety

  • Competitive salary and company benefits
  • Work-from-home arrangement
  • Career growth opportunities
  • Continuous learning opportunities
  • Global organization with flat structure
  • Innovative environment with autonomy

Related Jobs