Algorithm Engineer, LLM (Safety First) – AI Safety

Position: Algorithm Engineer, LLM (Safety First) – AI Safety

Location: Remote (Taipei, Taiwan)

Type: Full-time

Company: Binance

Role Overview:

Join Binance’s AI/ML team to develop safety frameworks and AI guardrails for large language models (LLMs) and intelligent agents. Focus on trust, compliance, and reliability in AI-powered products like chatbots, compliance systems, and token reports.

Responsibilities:

• Design and build AI guardrails frameworks for LLMs and agent workflows
• Define and enforce safety, security, and compliance policies
• Detect and mitigate prompt injection, jailbreaks, hallucinations, and unsafe outputs
• Implement privacy and PII protection measures (redaction, obfuscation, data residency)
• Develop red-teaming pipelines, automated safety tests, and risk monitoring tools
• Continuously improve guardrails for emerging threats and regulations
• Fine-tune/optimize LLMs for trading, compliance, and Web3 tasks
• Collaborate across Product, Compliance, Security, Data, and Support teams

Requirements:

• Master’s or PhD in Machine Learning, AI, Computer Science, or related field
• Research publications (ICLR, NeurIPS, ACL, ICML) are a plus
• Hands-on experience with LLM/agent guardrails (policy design, filtering, refusal rules)
• Practical experience mitigating hallucinations and safety evaluations
• Proven ability to deliver AI safety frameworks in production
• Strong Python coding skills; Java and PyTorch/TensorFlow/JAX expertise preferred
• Knowledge of privacy, PII handling, data governance, and risk frameworks
• Interest in crypto, Web3, and financial systems
• Self-driven, strong ownership, excellent communication skills

Why Binance:

• Shape the future with the world’s leading blockchain ecosystem
• Work with world-class talent in a flat, user-centric organization
• Autonomy on fast-paced, innovative projects
• Career growth and continuous learning opportunities
• Competitive salary, benefits, and remote work options