Enterprise GenAI at scale
Shipping agentic, RAG, and semantic-search systems for thousands of retail markets.
Highlights
TLDR: I ship production AI systems, and I can explain the engineering behind them.
Multi-agent systems
Built hackathon-winning developer-support agents and award-placing store-assistant extensions.
ML/MLOps delivery
Turns notebooks into deployed APIs, dashboards, retraining workflows, and monitored services.
Research depth
Peer-reviewed computational-mechanics background, with ML applied to scientific modelling.
Featured Projects
Semantic Product Search Engine
- Researched and evaluated search engine options for a second-hand e-commerce platform, selecting Meilisearch for its hybrid semantic/lexical search, bilingual Thai/English support, and cost profile at scale - saving months of in-house search development.
- Designed and deployed a real-time PostgreSQL → Meilisearch sync pipeline using logical replication and MeiliBridge, enabling sub-second product index updates without changes to the host application.
MeilisearchPostgreSQL real-time syncRustTypeScriptAxum
Motorbike Condition Evaluation
- Built a multi-modal ML regression pipeline fusing 39-dimensional MFCC audio features (extracted from inspection videos via librosa), Thai-language BERT embeddings (WangchanBERTa), and categorical inspection inputs to predict a 0-100 motorcycle condition score.
- Benchmarked 5 regression algorithms (ElasticNet, Random Forest, Gradient Boosting, SVR, XGBoost) with scikit-learn RandomizedSearchCV hyperparameter tuning; serialized the best-performing pipeline for cloud-hosted inference.
PythonPandasFastAPIscikit-learnXGBoost
Credit Risk Assessment
- Performed exploratory analysis and built a reproducible data-cleaning and transformation pipeline on a raw credit dataset.
- Ran model selection across candidate classifiers with per-segment personalized feature selection to sharpen credit-default discrimination.
PythonPandasscikit-learnStreamlit
Credit Default Prediction
- Built a full-lifecycle credit-default MLOps system: EDA, automated data-cleaning pipeline, MLflow experiment tracking, blue-green model selection, and Prefect-orchestrated automatic retraining.
- Ran a profit-optimized threshold simulation achieving a 30% profit increase on out-of-sample data versus a baseline cut-off policy.
PythonPandasscikit-learnFastAPIMLflow
Work with me
I take focused ML/AI engineering work for teams that need a system shipped, not a prototype. Typical engagements:
Ship a GenAI feature to production
RAG, agents, or LLM pipelines that survive real traffic, with the evals and observability to trust them.
Rescue a stalled ML project
Turn a notebook that works on a laptop into a deployed, monitored service.
ML infrastructure and MLOps
Experiment tracking, automated retraining, and CI for models.
How it works: a short scoping call, a fixed-scope first milestone, then iterate.
From the Blog
All posts →Let's talk
Open to Senior ML/AI engineering roles and freelance engagements. Email is the fastest way to reach me.