Haoming Koo.
AI Engineer · Singapore · Available from October 2026
AI Engineer · Singapore · Claude Certified ArchitectAI Engineer · Claude Certified Architect

Haoming Koo

Making AI systems you can rely on.

7 years at Micron building production systems for semiconductor operations, now at AI Singapore (AIAP) building a 100E industry AI solution.

[email protected] See the work →
7yrsMicron Technology
$600M+Program impact
8Public systems
Haoming Koo, applied AI engineer based in Singapore
Singapore · 1° 17′ N
2026 / Open
Scroll
How I build

I build AI systems the same way, from problem to production.

A clear problem statement, a design that survives scale, a working baseline, rigorous evaluation, and a deployment that keeps running after launch.

01
Clarify the problem
What decision this needs to support, and what success actually looks like.
02
Design for scale
Data flow, latency budget, and where the system has to bend as load grows.
03
Build the baseline
The simplest version that could plausibly work, shipped first.
04
Evaluate and optimize
Ground-truth sets, error analysis, and tuning against the metric that matters.
05
Ship with CI/CD
Tests, staged rollout, and monitoring so it keeps working after launch.
Core stack

Applied AI, from workflow to deployment.

The work spans the parts recruiters now screen for: LLM systems, retrieval, agents, evals, observability, ML models, APIs, data pipelines, and shipped user interfaces.

01

LLM systems

RAG, LangGraph, LangChain, MCP, tool-calling agents, SEA-LION, prompt management, human-in-the-loop workflows.

02

Evals and observability

Evaluation harnesses, Langfuse, Arize Phoenix, MLflow, trace review, failure analysis, source grounding.

03

ML and computer vision

LightGBM, scikit-learn, PyTorch, TensorFlow, YOLOv8, OpenCV, MediaPipe, SHAP, feature engineering.

04

Product engineering

FastAPI, React, TypeScript, Dash, SQLAlchemy, PostgreSQL, SQLite, auth, rate limits, background jobs.

05

Data and deployment

Docker, Railway, GitHub Actions, Playwright, APScheduler, GCP, AWS, Snowflake, Airflow, Kedro.

06

Enterprise delivery

Workflow automation, semantic search, text-to-SQL patterns, root-cause investigation, stakeholder reviews, cross-site rollout.

Current projects

Systems in production and active development. Start with the one closest to your problem.

Live
React FastAPI SEA-LION
Job Hunter SG
Singapore job-search product with resume parsing, semantic job matching, SEA-LION rewrites, and validation-gated scoring/export.
sentence-transformers SQLAlchemy LangGraph Railway
Live
FastAPI React LightGBM
Trader Koo
Market research system for equities, crypto, macro, options, and Polymarket. It stores source-fresh data, plots evidence, records paper trades, and sends Telegram alerts.
YOLOv8 SQLite APScheduler Telegram
MCP server
TypeScript MCP SDK Node HTTP
Japan in Seasons
Japan seasonal travel map, REST API, and MCP server with 17 read-only tools, live JMC/JMA data, Open-Meteo spot weather, and crawlable seasonal pages.
Zod Streamable HTTP Caching Railway
Live
Python Playwright GitHub Actions
Amex Explorer
Map-first explorer for Singapore Amex dining and hotel benefits. Python refresh scripts track official sources, source hashes, and cached Table-for-Two availability.
Source diffing Source hashes Scheduled refresh GitHub Pages
Live
React FastAPI LightGBM
LionWeather
Singapore weather app with live NEA ingestion, radar cache, saved locations, and LightGBM rainfall forecasts trained with temporal validation.
NEA API Recharts SQLAlchemy APScheduler
Live
FastAPI MediaPipe OpenCV
Photo Studio
Passport/ID photo rules engine with face landmarks, segmentation, crop/background assist, and country-profile checks.
rembg ONNX Runtime YAML profiles Docker
Live
Dash Plotly scikit-learn
Preflight
Dataset triage workbench for CSV/Parquet uploads: type inference, missingness checks, EDA charts, baseline classifiers, and CV metrics.
Pandas Gunicorn Docker CSV/Parquet
Live
FastAPI Selenium SQLAlchemy
MinMax Wine
Singapore wine deal engine with retailer scraping, bundle normalization, Vivino matching, LLM-assisted enrichment, and confidence-aware scoring.
PostgreSQL Brave Search Gemini Railway
About
2018 — 2025 Micron Technology

Led AI-enabled transformation across four fabs (Singapore, Boise, Hiroshima, Taichung), with a team of 6 direct and up to 9 indirect engineers and a $9M portfolio. Co-led low-power DRAM and HBM yield programs, described here without customer or internal programme details. Built ML risk-scoring that lifted yield 1–2% at production scale, a GenAI SOP workflow scaled to ~3,000 engineers, and a digital twin that cut chemical use 60%. ResNet-50 wafer-defect classifier (Innovation Award). Work identified $600M+ in opportunities, with $50M+ realized.

2026 — Now AI Singapore (AIAP) · 100E

Industry AI solution through the AIAP 100E programme, powered by SEA-LION and production ML patterns. Agents, vision, sequence modelling, RAG, evals, MLOps.

Always Building AI

I keep side projects practical: real URLs, real data where possible, validation gates, and clear boundaries when something is demo or research-only.

Full background, experience & skills →

Recent writing

View all ›
BuildingJul 17, 2026

A Visual Guide to Simulating a TSV from Etch to Polish

Building a TSV process simulation with ViennaPS: process handoffs, tunable inputs, failure modes, measurements, and model limits.

Read ›
AIJul 17, 2026

I Am Now a Claude Certified Architect. Here's What I Wish I Knew First.

What the Anthropic certification family covers, why I chose this track, what to prepare, and the paced game plan that got me there.

Read ›
BuildingApr 12, 2026

I Went from 64 to 100/100 on Smithery. Here's Every Fix.

MCP quality fixes: tool names, annotations, caching, Smithery config, and a reusable create-mcp skill.

Read ›

Need AI systems people can trust and use?

Singapore-based, available from October 2026 for applied AI, agent workflow, and LLM product engineering roles.

[email protected]