Mitchell McCallum

AI and Machine Learning Engineer specializing in RAG (Retrieval-Augmented Generation) and high-performance GenAI infrastructure. I architect enterprise semantic search layers utilizing vector embeddings and Snowflake Cortex AI to convert unstructured data into actionable intelligence. My expertise lies in engineering distributed data pipelines via Snowflake, Apache Spark, and Polars, specifically optimized for LLM-ready data delivery. I bridge the gap between data engineering and production AI by implementing robust MLOps/LLMOps frameworks and CI/CD pipelines using Airflow, Docker, and AWS.