At Bespoke Labs.ai, I built a RAG pipeline with automated model retraining and deployed LLM inference APIs on AWS. I used MLflow and DVC for experiment tracking and model versioning.
At Plat.AI, I built and deployed FastAPI-based ML inference services and engineered Python and Bash ETL/ELT pipelines that reduced manual processing by 15+ hours per week. I also worked with distributed data systems and monitoring dashboards.
My projects include an LLM data extraction platform, multi-agent AI workflows, and a Conversion Automation Engine that reduced lead-processing latency by 25%. I work across machine learning, data pipelines, and backend infrastructure.
