Research Engineer II (Computer Science / Cyber Security / Artificial Intelligence)

Nanyang Technological University Singapore; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

NTU Singapore, via the Alibaba-NTU Global e-Sustainability CorpLab (ANGEL), seeks a Research Engineer II to advance trustworthy AI and cyber security research focused on safety and access control for autonomous LLM agents. The role involves environment-aware, task-oriented access control, structured context profiling, and runtime adjudication of agent actions.

Responsibilities include designing profiling and policy agents, runtime guard mechanisms, and exploring reinforcement learning to improve

Qualifications

• Master's degree required in a relevant field (CS, Cyber Security, AI).
• Experience in AI/LLM agent safety, access control, systems security, or trustworthy ML.
• Familiarity with LLM-based agents, tool use, and multi-step reasoning.
• Knowledge of access-control concepts, least-privilege design, and runtime policy enforcement; RL experience is an advantage.
• Hands-on experience in fine-tuning large language models using PyTorch.

Responsibilities

• Conduct research on environment-aware, task-oriented access control for computer-use (Claw-like) agents, including context profiling and least-privilege policy generation.
• Design and implement a Profile-and-Policy Agent that constructs structured authorization context and generates task-oriented least-privilege permissions.
• Develop and evaluate a Runtime Guard Agent that reviews agent tool calls during execution and applies adaptive controls.
• Implement and experiment with optimization methods (e.g., reinforcement learning) to improve profiling and policy generation.
• Construct attack payloads and benchmarks (e.g., OpenClaw scenarios, WildClawBench) and benchmark against representative baselines.
• Contribute to manuscript drafts for top-tier venues and support proposal and grant documentation.

Skills

Python

C/C++

Java

Reinforcement learning

LLM safety

Education

Master's degree in Computer Science, Cyber Security, AI or related

Tools

PyTorch

Job description

The Alibaba-NTU Global e-Sustainability CorpLab (ANGEL) represents a key collaboration between Alibaba Group and Nanyang Technological University (NTU). Supported by the Singapore RIE2025 Fund, ANGEL creates and deploys impactful green digital technologies for global sustainability.

ANGEL’s mission aligns seamlessly with Singapore’s national objectives, such as the Singapore Green Plan 2030 and the Singapore Smart Nation Initiative. ANGEL’s work in developing sustainable and equitable digital solutions and promoting a sustainable and green lifestyle will contribute to a smaller carbon footprint. Its holistic approach will help to secure a brighter, more sustainable future for humanity.

ANGEL will also cultivate human talents equipped with both advanced technical skills and a solid understanding of sustainable practices. They will enable Singapore to realise its environmental and technological ambitions.

We are seeking to appoint a Research Engineer II who will contribute to NTU’s mission of advancing trustworthy AI and cyber security research, with a particular focus on the safety and access control of autonomous LLM agents. The Research Associate will conduct research on environment-aware, task-oriented access control for computer-use (“Claw-like”) agents, designing and implementing mechanisms for structured context profiling, least-privilege policy generation, and runtime adjudication of agent actions. The role will contribute to NTU’s strategic initiatives in building secure, reliable, and resilient AI agent ecosystems, while supporting collaborations across academia and industry under the guidance of senior researchers.

Key Responsibilities

• Conduct research on environment-aware, task-oriented access control for computer-use (“Claw-like”) agents, including context profiling and least-privilege policy generation.
• Design and implement a Profile-and-Policy Agent that constructs structured authorization context and generates task-oriented least-privilege permissions.
• Develop and evaluate a Runtime Guard Agent that reviews agent tool calls during execution and applies adaptive controls such as masking, logging, and approval.
• Implement and experiment with optimization methods (e.g., reinforcement learning) to improve profiling and policy generation.
• Construct attack payloads and benchmarks (e.g., OpenClaw scenarios, WildClawBench) and benchmark against representative baselines.
• Contribute to manuscript drafts for top-tier (CCF-A) venues and support proposal and grant documentation.

Requirements

• A 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 through coursework, projects, internships, or research.
• Familiarity with LLM-based and computer-use (“Claw-like”) agents, tool use, and multi-step reasoning.
• Knowledge of access-control concepts, least-privilege design, and runtime policy enforcement; RL experience is an advantage.
• Hands-on experience in fine-tuning large language models (e.g., supervised fine-tuning, reinforcement learning, or parameter-efficient methods such as LoRA) using frameworks such as PyTorch.
• Proficiency in programming languages such as Python, C/C++, and Java.
• Ability to contribute to academic writing and research outputs for international top-tier (CCF-A) conferences.

Hiring Institution: NTU