At Elastic, I develop Python ingestion and indexing pipelines for AI-powered search and document retrieval. I implement semantic and hybrid search with Elasticsearch and vector embeddings, and integrate LLM APIs into retrieval workflows for context-aware question answering.
At Capital One, I developed Python and SQL data pipelines and Apache Spark batch workflows for data transformation. I also implemented data-quality checks and supported AWS processing infrastructure.
At GitLab, I developed Python integration utilities for internal services and external APIs, created SQL transformations and maintained dbt models in Snowflake. I also maintained GitLab CI/CD workflows, testing, and validation checks for internal data services.
