Algorithm Engineer LLM Safety First – AI Safety

This role involves designing and building an AI Guardrails framework to ensure safety, security, and compliance for LLMs and agent workflows. Responsibilities include detecting and mitigating prompt injection, jailbreaks, hallucinations, and implementing privacy protections. The ideal candidate has a strong background in ML/AI, experience with LLM safety, and proficiency in Python and PyTorch/TensorFlow/JAX. The position is fully remote and focuses on AI safety in the crypto/Web3 space.

• 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

• Master’s/PhD in Machine Learning, AI, Computer Science, or related field
• Hands-on experience building LLM/agent guardrails (policy design, refusal rules, filtering, permissions)