As a Data-Centric AI Engineer, I architect and ship end-to-end data pipelines and machine learning systems that power scalable, production-grade AI applications. I design robust ETL workflows using Spark, Dask, and Apache Airflow; build high-throughput ingestion layers on AWS EMR, Redshift, Snowflake and Databricks; and optimize data stores with Python multithreading, file-splitting and S3 external stages. Leveraging infrastructure as code (Terraform, CloudFormation), containerization (Docker/Kubernetes) and CI/CD (GitHub Actions, GitLab CI), I ensure reliable, maintainable data platforms that serve real-time analytics and batch ML workloads.

As a Full-Stack AI Engineer, I translate complex ML models into seamless user experiences—developing interactive front-ends in React.js and Tailwind CSS, and implementing REST/GraphQL APIs with FastAPI, Node.js/Express or Spring Boot. I integrate vector databases (FAISS, Pinecone) and RAG workflows via LangChain to build intelligent document-retrieval interfaces, and orchestrate multi-agent LLM pipelines with Streamlit and LangFlow. My end-to-end approach spans data modeling and feature stores through inference services and scalable deployment on Kubernetes, backed by observability (Prometheus, Grafana, ELK) and automated retraining loops.

With a foundation in both software engineering and MLOps, I thrive at the intersection of data engineering and AI product development—turning raw data into high-impact insights, and research prototypes into user-facing applications that drive measurable business value.