Mohamed Saleh - Machine Learning Engineer (Part Time)

Recommended expert

Munich, Germany

Experience

Jun 2024 - May 2025

1 year

Germany

Designed and implemented an advanced, agentic RAG pipeline using LangChain and LangGraph for structured data extraction from PDFs, utilizing tools, state management, and OpenAI LLMs (GPT-4) to improve accuracy and handle complex document structures.
Developed a Google AI agent for extraction of structured information from PDF documents and deployed the agent on Vertex AI.
Architected data pipelines using Azure Data Factory and Databricks to ingest data from Azure Blob Storage, process it with PySpark, and load it into Azure SQL Database via Linked Services.
Containerized AI agents and services using Docker for consistent local development and deployment.
Utilized PySpark and Dask for database querying in coordination with Azure Blob Storage and Document Storage.
Created a ReAct agent that extracts structured data from PDF documents using tools and integrating Azure Document Intelligence.
Contributed to the CPO invoices validation check project using Databricks to find existing CDRs and calculate total valid costs.
Developed a conversational AI agent (chatbot) with a FastAPI backend, integrating RAG for precise tariff extraction and deployed the service using Azure Container Apps.
Tools used: Azure, Azure OpenAI, Azure Document Intelligence, Azure Blob Storage, Google ADK, Google Cloud, Vertex AI, Gemini, Databricks, LangChain, LlamaIndex Ollama, Docker, PySpark, Azure SQL, Azure Data Factory, Azure AI Agent, Microsoft SQL Server

Mar 2023 - Aug 2023

6 months

Germany

Fine-tuned code LLMs from Hugging Face for C++ code generation based on transformation rules used in health insurance policies.
Engineered a ReAct AI agent using LlamaIndex and CodeLlama for automated C++ code generation, demonstrating proficiency in agentic design patterns.
LLMs used: Code-T5, Polycoder, Incoder, CodeLlama.

Sep 2021 - Mar 2024

2 years 7 months

Germany

Led student application projects for training ML algorithms and monitored ML experiments using MLflow and MLOps.
Assisted in teaching and coding machine learning concepts.

Aug 2020 - Mar 2021

8 months

United States

Built and deployed a RAG system as a Flask web service on AWS, showcasing full-stack AI application development skills for an automatic positioning system of images and a table of contents generation system.
Libraries used: dlib, OpenCV, NumPy, Transformer T5, BERT, BART.

Jan 2020 - Feb 2024

4 years 2 months

United States

Developed an automatic categorization system using word similarity and deep learning.
Built a question generation application from cartoon images for an educational institution.
Created a ride price prediction model for NYC taxi rides data using XGBoost on big data stored in S3 buckets with Amazon SageMaker and Unified Studio.
Implemented an Arabic question answering system for labor law in Saudi Arabia using information retrieval techniques.
Developed an object detection system for passenger detection.
Built a pneumonia detection system with ResNet achieving classification accuracy of 97% and 91%, deployed as a Flask website on Heroku.
Created an audio recognition system using unique hashes (similar to Shazam) leveraging image processing techniques with Python and SQL.

Ai Agent Frameworks & Llms: Langchain, Langgraph, Llamaindex, Azure Ai Agent, Google Vertex Ai, Openai Gpt-4, Hugging Face, React Agent Pattern
Cloud & Azure Services: Azure Container Apps (Aca), Azure Functions, Azure Ai Search, Azure Document Intelligence, Azure Blob Storage, Azure Key Vault, Azure Log Analytics, Azure Service Bus, Azure Sql Database, Azure Data Factory, Azure Cli
Python Development: Python (Oop, Design Patterns), Async Programming, Fastapi, Flask, Sqlmodel, Sqlalchemy, Pytest
Data & Ml Engineering: Pyspark, Databricks, Dask, Docker, Docker Compose
Devops & Tools: Git, Docker, Ci/cd, Scrum, Jira
Databases & Drivers: Microsoft Sql Server, Pymongo, Redis-py