Data engineer with 10+ years building production data pipelines at scale, with experience in tier-1 financial institutions where data accuracy is non-negotiable.

I've spent a decade preparing analysis-ready datasets for data scientists and ML teams, productionizing models with internal tooling, and shipping reliable systems where mistakes cost real money.

These days I'm focused on combining that engineering rigor with LLM-powered intelligence — building tools that turn messy real-world data into clean, structured, model-ready outputs.

• Data engineering — pipelines, cleaning, validation, transformation at scale
• LLM applications — sentiment analysis, classification, enrichment, structured extraction
• Data science enablement — preparing trustworthy datasets that data scientists actually use
• ML productionization — taking models from notebook to production reliably
• Multi-language data processing — pipelines that handle global data sources

I build tools the same way I'd build them for a Fortune 500 client: secure, observable, and built to handle real edge cases — not toy demos.