Arslan Aslam

Data Engineer with hands-on experience building and orchestrating batch and real-time ETL pipelines processing data from 10+ sources using Python, SQL, Apache Airflow, Kafka, and AWS. Built production-grade RAG pipelines and LLM-powered applications using LangChain and LangGraph, combining data engineering foundations with applied AI to deliver intelligent, scalable data solutions.

Data Engineer Intern at BALANX-Bio (2025-01 – Present)

• Built and maintained end-to-end RAG (Retrieval-Augmented Generation) pipelines using LangChain, enabling semantic retrieval over 50K+ enterprise documents and reducing manual data lookup time by approximately 40%
• Developed and tested scalable AI/data pipelines with structured unit testing and validation checks, improving workflow reliability and reducing pipeline failures by 30%
• Optimized ETL processes across 5+ data sources, improving data freshness from daily to near real-time and ensuring consistent, accurate downstream reporting
• Integrated vector embeddings and AI-driven workflows into existing infrastructure by collaborating with cross-functional teams, laying the groundwork for intelligent search capabilities

Bachelor of Science in Computer Science – Institute of Space Technology Islamabad (2024-09 – 2028-09)