Safwan Ullah Khan

- Optimized ETL data pipelines on AWS using Spark to accelerate data processing. - Enhanced data validation with GreatExpectations, reducing downstream errors by 40%. - Designed interactive dashboards with Streamlit and executed fast queries using DuckDB, cutting load times by 30%. - Leveraged BigQuery for fast and accurate analysis on large datasets, reducing issue resolution time by 30%. Integration of LLM into Data Pipeline: - Researched and implemented LLMs like Gemini to enhance web scraping, focusing on efficient HTML structure segregation and data extraction accuracy. - Integrated the model into a spider, automating the process of extracting relevant data, improving scraping performance, and reducing errors in complex HTML pages.

Assisted in helping and organizing meetings for delegations. Participated in UNESCO meetings and conferences. Accomplished the efficient organization and handling of all document filing tasks and communication.