CV
Research interests
AI alignment and safety, including evaluations of eval-awareness and agentic misalignment, scalable alignment training, alignment pretraining, and mechanistic interpretability.
Experience
- Independent AI Safety Researcher — current.
- Machine Learning Engineer, TikTok — March–September 2026.
- AI Safety Research Intern, Huawei International — July–December 2025.
- MATS exploratory stage, advised by Neel Nanda — spring 2025. Mechanistic interpretability research.
- Equipment Engineer, Qualcomm — 2020–2022.
Education
- PhD in Computer Science, Nanyang Technological University — 2022–2026. Advisor: Prof. Erik Cambria.
- Bachelor in Mechanical Engineering with Honours (Distinction), Nanyang Technological University — 2017–2020.
Publications
See my publication list and Google Scholar profile.