AI Safety & Governance Engineer (SAGE)

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.

Duties & Responsibilities:

- Execute automated LLM safety testing pipelines integrated with GitLab CI/CD as mandatory gate before project delivery.

- Conduct red teaming and adversarial testing: 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.

- Support compliance with AI safety standards: 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.

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.

- Security Testing: Experience with vulnerability assessment, adversarial testing, or penetration testing. Understanding of LLM-specific vulnerabilities (prompt injection, jailbreaking, data leakage).

- Systems Design: Ability to review system architectures for security vulnerabilities and recommend secure design patterns for agentic, multimodal, and RAG applications.

- Software Engineering: Proficient Python skills with commitment to clean, maintainable code. Experience with testing frameworks (pytest, unittest).

- DevOps & Automation: Familiarity with Git, Docker, and CI/CD pipelines (GitLab or GitHub).

- Documentation: Strong technical writing skills for vulnerability reports and compliance evidence.

- Collaborative Mentor: Eager to guide AIAP apprentices and contribute to SAGE's supportive team culture.

We regret that only shortlisted candidates will be notified.

Hiring Institution: NTU