AI Scientist at Apodex · Singapore
My current work focuses on large-scale pretraining data acquisition and quality.
Previously, I built Apodex’s deep-research agent harness from scratch and led its core architecture. At A*STAR, I led data and evaluation for MERaLiON AudioLLM, co-led model training, and led AudioBench and SeaEval, published at NAACL. I’m interested in turning AI research and engineering into useful products.
01 / Research into practice
01Apodex · May 2026–present
Built pretraining data infrastructure from scratch, evolving on-demand fetching into offline batch processing and integrating domain quality assessment with lightweight URL scoring to guide acquisition.
An acquisition pipeline covering raw HTML, PDFs, and other information-rich documents, with quality scoring to guide collection.
02Apodex · May 2025–May 2026
Built the agent harness from scratch and led its core architecture as development grew to four or five contributors. Designed multi-source verification, parallel tool use, and multi-agent coordination.
A model and workbench for complex research, alongside the open-source FrontierAgent harness.
03I²R, A*STAR · 2023–2025
Led data preparation and evaluation, and co-led model training within a six-person team at A*STAR I²R.
MERaLiON AudioLLM, presented at ACL 2025 System Demonstrations, as part of Singapore’s National Multimodal LLM Programme.
02 / ESSAYS & NOTES
How research, career choices, a relationship, immigration, and chance all played a part in my decision to leave the United States for a postdoc in a country I had never visited.
Research intern openings at Apodex in Singapore. Onsite, paid, 3-6 months minimum. Below is the position and how to apply.
03 / A conversation
A small agent built on my public writing. Ask about my research, career, or life.
How it worksAnswers are generated from my public material and may be wrong. For anything important, contact me directly.