I build AI-powered applications, data-intensive systems, and scalable backend infrastructure.
I'm a Software Engineer interested in building systems at the intersection of AI, data, and backend infrastructure.
My work focuses on:
- AI Engineering — LLM applications, RAG, AI agents, and model-powered products
- Data Systems — ETL pipelines, analytics platforms, data processing, and MLOps
- Backend & Infrastructure — APIs, databases, containers, observability, and cloud-native systems
I enjoy taking a problem from data ingestion → backend services → AI workflows → observability → user-facing products and turning it into a complete, maintainable system.
Building practical AI systems rather than isolated model demos.
- LLM applications and AI-powered products
- RAG pipelines and vector search
- AI agents and tool-based workflows
- LLM inference, evaluation, and observability
Designing pipelines that transform raw data into useful products and insights.
- Data ingestion and ETL
- Analytics pipelines
- MLOps and model workflows
- Data platforms and automation
Building the foundation that makes applications reliable and operational.
- Backend APIs and service architecture
- PostgreSQL and data storage
- Docker and containerized applications
- Monitoring and observability
- Cloud and automation
An AI-powered engineering knowledge platform for discovering, searching, summarizing, and organizing technical content.
Highlights: AI-powered search · Summarization · Topic classification · Bookmarking
Tech: React Cloudflare Workers Workers AI D1 R2 GitHub Actions
A knowledge retrieval platform for ArXiv papers, combining automated ingestion, hybrid search, vector retrieval, and RAG to make technical research easier to explore.
🏆 Selected for the 17th iThome Ironman Contest — 2025 Excellence Award
Highlights: Data ingestion · Hybrid retrieval · Vector search · RAG · LLM · Observability
Tech: FastAPI Prefect Qdrant PostgreSQL MinIO Ollama React Prometheus Grafana
An end-to-end MLOps platform for stock price prediction, covering data pipelines, training, experiment tracking, inference, deployment, and monitoring.
Highlights: ETL · Model training · Experiment tracking · Inference · Monitoring
Tech: Prefect MLflow FastAPI PostgreSQL ClickHouse Prometheus Grafana Docker
A data engineering pipeline that processes GitHub activity data and transforms it into analytics insights.
Highlights: Data ingestion · Workflow orchestration · BigQuery analytics · Dashboard
Tech: Python Airflow BigQuery GCP Terraform Streamlit
MATLAB
LLM RAG Ollama Hugging Face MLflow Qdrant
ClickHouse Qdrant
Airflow Prefect BigQuery ETL Data Pipelines
Langfuse
- AWS Certified Cloud Practitioner· Amazon
- Associate Data Practitioner Certification· Google
- Google AI Professional Certificate· Coursera
- Ultimate AWS Certified Solutions Architect Associate 2026 · udemy
- MLOps Zoomcamp · DataTalks Club
- Data Engineering Zoomcamp · DataTalks Club
- LLM Zoomcamp · DataTalks Club
- Generative Adversarial Networks (GANs) Specialization · Coursera
- Google Data Analytics · Coursera
- Data Science Fundamentals with Python and SQL Specialization · Coursera
- Accelerated Computer Science Fundamentals Specialization · Coursera
- Deep Learning Specialization · Coursera
- Python for Everybody Specialization · Coursera
Building systems, learning continuously, and turning ideas into working products.




