Cairo, Egypt Remote
AI & data engineer with a data engineering foundation and hands-on training at Samsung Innovation Campus, NTI, and DEPI. I build production RAG systems and ELT/ETL pipelines with PySpark, Airflow, dbt, and Snowflake, model warehouse layers, and enforce data quality so analytics and ML teams can rely on their datasets. I enjoy turning raw, messy sources into clean, dependable systems that are easy to build on.
Python
PySpark
Airflow
AWS
Snowflake
dbt
Databricks
PostgreSQL
Kafka
Docker
FastAPI
LangChain
Redis
MongoDB
Power BI
Linux
Git
Built a grounded RAG pipeline over 21 recipe documents (~73 chunks) using ChromaDB, HyDE retrieval, and Llama 3.2:3b for generation. Exposed 3 tools via FastMCP in Claude Desktop with 100% top-5 retrieval precision and 4.7/5 average answer relevance.
Co-built an end-to-end ELT pipeline for NYC Yellow Taxi data: Airflow-orchestrated ingestion from AWS S3 (Lambda) into Snowflake, with dbt medallion models (staging, intermediate, marts). Engineered a real-time layer using FastAPI, Kafka, Spark Streaming, and Redis flagging trips across 15+ rules.
Co-built a FastAPI backend featuring a RAG pipeline (LangChain + FAISS) that retrieves clinical context from medical PDFs/CSVs, generating answers with Llama 3 (Together AI). Paired with a Streamlit UI and a pytesseract OCR module to extract text from medical prescriptions.
Collaborated in a team to build a distributed PySpark ETL pipeline joining raw CSV sources (orders, customers, products, logistics) into a single clean fact table ready for Power BI reporting.
Engineered scalable distributed pipelines using PySpark and Spark SQL. Processed and transformed large-scale e-commerce datasets into high-performance dimensional star-schema models.
Built production NLP pipelines with LangChain, FAISS, TF-IDF cosine-similarity recommenders, and containerized backends deployed via FastAPI.
Automated AWS infrastructure deployments using AWS CLI scripting. Architected and configured private VPC Peering connections, Route Tables, and Security Groups monitored via Amazon CloudWatch.
Faculty of Artificial Intelligence, Kafr El-Sheikh University · GPA: 3.66 / 4.0
Deep focus on algorithms, machine learning systems, statistical computing, and distributed data structures.
Participant in Dev Days (GitHub Community Event hands-on workshop on Copilot and prompt engineering, Oct 2026).
EPIC Institute of Technology
Two-semester program covering algorithms and data structures, distributed systems architecture, real-time backend engineering, and applied generative AI solutions.