Research Engineer II – AI & Cybersecurity for Autonomous LLM Agents

About the role

We are looking for a Research Engineer II to join the Alibaba‑NTU Global e‑Sustainability CorpLab (ANGEL) in Singapore. The role focuses on trustworthy AI and cyber‑security research, specifically on safety and access‑control mechanisms for autonomous large‑language‑model (LLM) agents that interact with computer environments.

Key responsibilities

• Design and implement a Profile‑and‑Policy Agent that builds structured authorization contexts and generates task‑oriented least‑privilege permissions.
• Develop a Runtime Guard Agent that monitors tool calls during execution, applying adaptive controls such as masking, logging, and approval.
• Research environment‑aware, task‑oriented access control for “Claw‑like” agents, including context profiling and policy generation.
• Apply optimisation methods, e.g., reinforcement learning, to improve profiling and policy generation.
• Create attack payloads and benchmarks (OpenClaw scenarios, WildClawBench) and evaluate against representative baselines.
• Contribute to manuscript drafts for top‑tier (CCF‑A) venues and support proposal and grant documentation.

Required profile

• Master’s degree in Computer Science, Cyber Security, Artificial Intelligence or a related discipline.
• Research or applied experience in AI/LLM agent safety, access control, system security, or trustworthy machine learning.
• Familiarity with LLM‑based and computer‑use (“Claw‑like”) agents, tool use, and multi‑step reasoning.

Required skills

• Reinforcement learning
• LLM agents
• Access control mechanisms