AI Safety Research Associate – Computational Linguistics & CS

About the role

The AI Safety Research Associate will join AI Singapore’s national AI programme, hosted at Nanyang Technological University. The role focuses on developing safety and alignment strategies for large language models (LLMs) in the medical domain and for Southeast Asian languages.

Key responsibilities

• Co‑design and implement safety and alignment strategies for LLMs targeting medical applications.
• Develop guardrails and safeguard models to mitigate risks.
• Analyse failure modes specific to Southeast Asian languages and cultural contexts.
• Support the creation of regional language capabilities for the SEA‑LION project.
• Identify culturally grounded safety risks and ensure systems generalise beyond English‑centric assumptions.
• Design leaderboards and visualisations for auditable reporting of results.
• Co‑author top‑tier publications (ACL, EMNLP, NeurIPS, ICLR, etc.).

Required profile

• Preferably a Master’s degree in Computational Linguistics, Computer Science, or equivalent practical experience.
• Experience in safety alignment for LLMs, model evaluation for safety or robustness, and a track record of publications in safety research.
• Strong communication skills for collaborative work.

Required skills

• Python programming.
• Natural Language Processing (NLP) concepts.
• LLM inference frameworks such as Ollama or vLLM.
• Generative AI and LLM models (e.g., Llama, Gemma, Qwen).
• Designing leaderboards and data visualisation.