AI Safety & Governance Engineer (SAGE)
- Singapore
- Mid Level
- Posted
We regret that only shortlisted candidates will be notified.
About Ntu
AI Singapore (AISG) is a national initiative driven by the Ministry of Digital Development and Information (MDDI), the Infocomm Media Development Authority (IMDA), and the National Research Foundation, Singapore (NRF).
AISG brings together Singapore-based research institutions and the broader ecosystem of AI start-ups and companies to support impactful research, develop talent and power Singapore's AI efforts.
For more information on AI Singapore, please visit https://www.aisingapore.org .
This position will be hosted at the Nanyang Technological University (NTU) under VP (Artificial Intelligence & Digital Economy)’s office and we welcome you to join our community.
Responsibilities
- Execute automated LLM safety testing pipelines integrated with GitLab CI/CD as mandatory gate before project delivery.
- prompt injection, jailbreaking, data leakage, RAG poisoning, multi-turn attacks.
- Review LLM system architectures (agentic, multimodal, RAG) for security vulnerabilities and provide design recommendations.
- Document vulnerabilities with severity ratings, reproduction steps, and remediation guidance.
- ISO 42001, NIST AI RMF, OWASP LLM Top 10, MITRE ATLAS, Singapore Model AI Governance Framework.
- Train and mentor AIAP apprentices on responsible AI engineering during deep-skilling and project phases.
- Contribute to AI Singapore's community-building activities through talks, workshops, and documentation.
- Ability to review system architectures for security vulnerabilities and recommend secure design patterns for agentic, multimodal, and RAG applications.
- Strong technical writing skills for vulnerability reports and compliance evidence.
Requirements
- Degree with at least 2-4 years of work experience.
- Appointment at senior level may be considered based on relevant experience.
- We welcome applicants from all disciplines who can demonstrate the following skills: LLM/GenAI Systems: Working knowledge of LLM architectures, prompt engineering, RAG implementations, and API integration.
- Experience with vulnerability assessment, adversarial testing, or penetration testing.
- Understanding of LLM-specific vulnerabilities (prompt injection, jailbreaking, data leakage).
- Proficient Python skills with commitment to clean, maintainable code.
- Experience with testing frameworks (pytest, unittest).
Preferred
- Familiarity with Git, Docker, and CI/CD pipelines (GitLab or GitHub).
- Eager to guide AIAP apprentices and contribute to SAGE's supportive team culture.
Hiring Institution
NTU
