Applied ML / AI Engineer
I build ML systems that ship, not just notebooks that demo.
Document extraction, retrieval-augmented generation, and the serving infrastructure that keeps applied AI running in production.
How I build
I start from the failure modes, not the demo: what breaks when the input is messy, the latency budget is tight, or the model is wrong with confidence. Systems get built in thin, observable slices — one pipeline stage, one endpoint, one dashboard at a time — so every layer ships with the logging and guardrails it needs to be trusted in production, not just in a notebook.
Stack
- LanguagePython
- ML ToolingRAG / Hybrid Search
- ServingFastAPI
- FrontendNext.js / TypeScript
- PackagingDocker
- DeploymentRailway
- OrchestrationKubernetes / Helm
- Experiment TrackingMLflow
- ObservabilityPrometheus / Grafana
Projects
docfield-extract
LiveDocument field-extraction pipeline with rule-based validation, benchmarked on ICDAR 2019 SROIE.
- Python
- OCR
- Rule Engine
- ICDAR SROIE
gofetch
LiveRAG pipeline built from scratch — hybrid search, cross-encoder re-ranking, a knowledge graph, and streaming answers with inline citations.
- Hybrid Search
- Cross-Encoder
- Knowledge Graph
- Streaming
RocketML
LiveNLP model launchpad — FastAPI serving, Docker, CI to GHCR, MLflow tracking, Prometheus/Grafana, Helm on Kubernetes.
- FastAPI
- Docker
- MLflow
- Prometheus
- Kubernetes
- Helm
GotParking
LiveSingapore parking-availability lookup, updated in near real time.
- Next.js
- TypeScript
- Geospatial
Experience
- 2024 — Present
Applied ML / AI Engineer — Placeholder — Company Name
Placeholder summary. Real role details, dates, and impact metrics go here.
- 2022 — 2024
Placeholder Role — Placeholder — Company Name
Placeholder summary. Structure of this timeline is final; copy is not.
- 2020 — 2022
Placeholder Role — Placeholder — Company Name
Placeholder summary for an earlier role or project.