Research Engineer I – AI & Cyber Security

About the role

The Alibaba-NTU Global e‑Sustainability CorpLab (ANGEL) is seeking a Research Engineer I to advance trustworthy AI and cyber‑security research. You will focus on the runtime safety of autonomous coding agents and contribute to safe reinforcement‑learning methods for long‑horizon, executable environments.

Key responsibilities

• Assist in conducting research on safety alignment of executable coding agents using reinforcement learning in long‑horizon repository‑and‑shell environments.
• Support the construction of RL training datasets by collecting, synthesising, and organising coding‑agent trajectories, including benign and safety‑critical scenarios.
• Implement agent‑safety RL training for SWE‑agent‑like coding agents using base models from the Qwen3.5 family.
• Build and maintain controlled sandbox environments for trajectory sampling, training, and evaluation.
• Run experiments to evaluate safety improvements and utility preservation, and summarise results.
• Assist in manuscript preparation and contribute to proposal and grant documentation.

Required profile

• Bachelor's degree in Computer Science, Artificial Intelligence, Cyber Security, or a related discipline.
• Research or applied experience in reinforcement learning, LLM training, AI safety, or coding agents through coursework, projects, internships, or research activities.
• Basic experience with or strong interest in LLM‑based coding agents, agent harnesses, and tool/terminal execution.
• Knowledge of RL training processes and safety‑critical scenario design.

Required skills

• Reinforcement learning
• LLM training
• AI safety
• Coding agents
• Qwen3.5 model family
• Sandbox environments
• Repository‑and‑shell environments