01About
Mostly, I want to know how things actually work.
I'm a senior data scientist at C3 AI. My path ran through Singapore and New York before the Bay Area: a BE in Computer Science from NTU, a stretch of internships from Shopee to Seagate, then an MS at Columbia with a focus in machine learning. The constant across all of it has been a stubborn kind of curiosity, the sort where I'll re-implement an idea from scratch just to find out how it actually works.
These days that curiosity has a job. At C3 I sit with customers, translate a vague business problem into something a model can answer, and carry it all the way to production. That's mostly probabilistic time-series forecasting, with some RAG-based LLM systems along the way. I care about three things in particular: models you can interpret, deployments you can reproduce, and tooling that makes the next engineer's job easier.
02Work
What I've worked on.
- Customer-facing lead on our largest forecasting engagements, owning projects from problem definition to production
- Lead demand forecasting for the server business unit at a leading semiconductor company
- Previously led yield forecasting at the world's largest berry producer, generating ~$5M in annual value
- Manage release for our forecasting packages and mentor data scientists across teams and projects
- Led demand forecasting for the largest CPG company in Guatemala, generating $2.3M in annual impact
- Built a RAG-based LLM system for low-latency, policy-compliant document retrieval across C3 AI's internal documentation
- Built and owned DRIPP, an internal Python deployment toolchain that reduced deployments from hours to minutes
- Owned MetaML, the internal orchestration tool for time-series deployments
- Led release management for forecasting packages, enforcing coding and packaging standards across teams
Shipped an out-of-the-box hierarchical forecasting and reconciliation system, using post-hoc MinT/ERM and intrinsic DeepVAR-Hierarchical approaches for cross-level coherence, and integrated probabilistic forecasts with Integrated Gradients explainability so the outputs were both uncertainty-aware and interpretable.
Built a tree-based sales forecasting model for seasonal planning, a 95%+ accuracy image-similarity engine for product matching, and an order-management web app that improved accuracy while cutting manufacturing costs and stockouts.
A run of hands-on ML and data work: optimizing Airflow/HDFS pipelines and a compression tool that cut storage by 90%+ at Shopee; neural-net and tree models to forecast hard-drive test time at Seagate; a React and Rails KPI dashboard at Outstrip; and a two-stream I3D action-recognition model on AWS SageMaker for early autism screening at CogniAble.
03Projects
Most of these began as “I don't really get this, let me build it.”
04Education
Where the fundamentals came from.
05Contact
This page grows as I do, so it's never really finished. If something here resonates, my inbox is open.
