Data Scientist and AI Engineer focused on multi-agent systems, scalable data engineering, and production ML. I build systems that are useful, traceable, and ready for real workloads.
|
Ingest |
Refine |
Activate |
|
Streaming and batch ingestion across Kafka, Spark, and cloud storage — landing raw, messy data reliably. |
Cleaning, conforming, and modelling with dbt and Delta Lake, with quality checks and observability built in. |
Decision-ready output: RAG systems, multi-agent workflows, dashboards, and deployed models. |
🐍 A snake eating its way through my GitHub contribution graph — every square it swallows is a day I shipped code. Regenerated every day at midnight by GitHub Actions, and it adapts to your light/dark theme.
|
|
| Project | What it shows |
|---|---|
| 1-Trillion-AI-Problem | Applied AI problem framing and prototype delivery |
| Autonomous-Multi-Agent-Research-Action-System | Multi-agent orchestration and research workflows |
| RAG-Ready-Web-Corpus-Builder-using-OpenClaw | Retrieval-ready corpus generation pipeline |
| Agentic-Early-Warning-Intelligence-System-for-Silent-System-Failures | Agentic monitoring and early-warning detection |
📈 Streak and contribution curve for the past year. The curve is rendered by my own workflow straight from the GitHub GraphQL API — no third-party service to go dark on me — and follows your light/dark theme.
- Advanced RAG evaluation and retrieval quality
- Multi-agent orchestration patterns
- Production-grade data pipelines and monitoring
- Model deployment, automation, and reliability
If you want to talk about AI systems, data engineering, or freelance work, reach out here:
- LinkedIn: https://www.linkedin.com/in/somesh-ghaturle/
- Email: someshghaturle@gmail.com
- GitHub: https://github.com/somesh-ghaturle




