Data professional with a deep passion for turning raw data into intelligence. I bridge the gap between data engineering, data science, and emerging AI — building pipelines, training models, and orchestrating intelligent systems that make data work smarter.
A committed home labber, I design and maintain my own infrastructure for experimenting with LLMs, autonomous agents, distributed systems, and real-time data processing — because the best way to understand a technology is to build with it yourself.
"Data is the raw material. Intelligence is the finished product."
|
Scalable ETL/ELT pipelines, data warehousing, stream processing, and workflow orchestration.
|
LLM agents, RAG pipelines, model fine-tuning, and production ML serving.
|
Self-hosted LLM inference, container orchestration, monitoring, and automation.
|
| Domain | Technologies |
|---|---|
| Languages |
|
| Data Engineering |
|
| Databases |
|
| Cloud & Infra |
|
| AI / ML |
|
| Visualization |
|
| Certification | Badge |
|---|---|
| Microsoft Certified: Fabric Analytics Engineer Associate |  |
| Microsoft Certified: Power BI Data Analyst Associate |  |
| Microsoft Certified: Azure Data Engineer Associate |  |
| Microsoft Certified: Azure Data Scientist Associate |  |
| Microsoft Certified: Azure AI Fundamentals |  |
| Microsoft Certified: Azure Data Fundamentals |  |
All certifications are active and maintained through continuous learning on the Microsoft Learn platform.
I run a self-hosted research environment for experimenting with AI and infrastructure:
| Capability | Stack |
|---|---|
| LLM Inference | Ollama, vLLM — 10+ models self-hosted |
| AI Agents | Hermes Agent, LangChain, custom workflows |
| Orchestration | Docker, Kubernetes, CI/CD pipelines |
| Monitoring | Prometheus, Grafana, self-hosted dashboards |
| Automation | n8n, cron-based scheduled tasks, event-driven pipelines |
- Autonomous AI agents — Multi-agent orchestration, tool-use, and persistent memory
- LLM serving & optimization — Quantization, speculative decoding, prompt caching
- Real-time data pipelines — Streaming analytics with Kafka + Flink + Trino
- Home lab reliability — GitOps, IaC, infrastructure-as-code for self-hosted services
Built with data, curiosity, and Python.