AI Safety & Governance Engineer (SAGE)
Core
Execute safety testing, conduct red teaming, review system architectures, and support governance for LLM/GenAI systems deployed through AI Singapore's 100 Experiments programme.
Role type
Senior IC AI Safety & Governance Engineer
Builds
Safe, secure, and compliant LLM/GenAI systems for project sponsors
Domain
AI Safety, Governance, LLM Security
Deliverable
production ML models
Required skills
LLM/GenAI systems knowledge, adversarial testing, systems design review, Python, CI/CD pipelines, technical documentation
Preferred skills
Red teaming experience, mentorship of apprentices
Technologies
GitLab CI/CD, Docker, Git, pytest, unittest
Responsibilities
Execute automated LLM safety testing pipelines; Conduct red teaming and adversarial testing; Review LLM system architectures for vulnerabilities; Document vulnerabilities with severity ratings; Support compliance with AI safety standards; Train and mentor AIAP apprentices
Seniority
Senior, hands-on IC