Skip to content
View msaleh1888's full-sized avatar

Block or report msaleh1888

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
msaleh1888/README.md

👋 Hi, I'm Mahmoud — AI Engineer & Cloud-AI Developer

I build practical, production-ready AI systems:
machine learning models, FastAPI microservices, Azure ML pipelines, serverless APIs, and RAG (Retrieval-Augmented Generation) applications.

My background includes 10+ years developing complex embedded software at Valeo and Garrett, and today I focus on applied AI, cloud deployment, and LLM-powered systems.

What I Do

  • Machine Learning & Deep Learning
    PyTorch, torchvision, transfer learning, model evaluation, feature engineering, embeddings.

  • FastAPI Microservices
    Clean inference APIs, health checks, modular architecture, Dockerized deployments.

  • Azure Cloud Engineering
    Azure ML (jobs, batch endpoints, model registry),
    Azure Functions (serverless APIs),
    Azure Document Intelligence (invoice extraction).

  • LLMs & RAG Systems
    Vector databases, ChromaDB, SentenceTransformers, Groq LLMs, retrieval pipelines, grounded responses.

  • Engineering Practices
    System design, clean code, documentation, reproducible repos, environment management, CI/CD.

📂 Featured Projects

Here are some of the projects that represent my current work:

🔹 Azure Customer Segmentation Pipeline

End-to-end ML pipeline using Azure ML Batch Endpoints, with engineered features and reproducible YAML infrastructure.
https://github.com/msaleh1888/azure-ml-customer-segmentation

🔹 Azure Serverless Invoice Extraction API

Invoice → structured JSON using Azure Functions + Azure Document Intelligence, CI/CD, monitoring.
https://github.com/msaleh1888/azure-serverless-invoice-extraction

🔹 RAG Microservice (FastAPI + ChromaDB + Groq)

Document ingestion, embeddings, vector DB, and /ask endpoint for grounded LLM answers.
https://github.com/msaleh1888/rag-llm-fastapi-microservice

🔹 Intel Natural Scenes API

Production-grade FastAPI microservice around a fine-tuned PyTorch ResNet18 model.
https://github.com/msaleh1888/intel-natural-scenes-api

🔹 Intel Natural Scenes Classifier

Two-phase transfer learning workflow with exported model artifacts.
https://github.com/msaleh1888/intel-natural-scenes-resnet18

🔹 Flower Image Classifier

VGG/ResNet classifier with training scripts, checkpoints, and CLI prediction.
https://github.com/msaleh1888/image-classifier

Tech Stack

Languages: Python, SQL
ML: PyTorch, torchvision, scikit-learn
Cloud: Azure ML, Azure Functions, Azure Storage
APIs: FastAPI, REST
RAG/LLMs: SentenceTransformers, ChromaDB, Groq
DevOps: Docker, GitHub Actions
Tools: Pandas, matplotlib, VS Code, Jupyter

What I'm Interested In

  • Remote AI/ML engineering roles
  • Cloud-based AI development
  • ML APIs, automation systems, and document AI
  • Production RAG systems
  • Freelance and contract work in applied AI

Contact Me

If you're working on something interesting in AI, cloud, or automation — I’d love to connect.

Pinned Loading

  1. intel-natural-scenes-resnet18 intel-natural-scenes-resnet18 Public

    A clean, well-structured PyTorch project where I trained a ResNet18 model on the Intel Natural Scenes dataset. The repo includes modular code, a simple training pipeline, full documentation, and a …

    Jupyter Notebook

  2. intel-natural-scenes-api intel-natural-scenes-api Public

    FastAPI + Docker inference service for my fine-tuned ResNet18 Intel Natural Scenes classifier. Upload an image and get real-time scene predictions with confidence scores.

    Python

  3. rag-llm-fastapi-microservice rag-llm-fastapi-microservice Public

    Production-ready Retrieval-Augmented Generation (RAG) microservice using FastAPI, ChromaDB, SentenceTransformers, Grok (xAI), and Docker. Supports TXT/PDF ingestion, vector search, and LLM-based qu…

    Python

  4. azure-ml-customer-segmentation azure-ml-customer-segmentation Public

    Production-grade customer segmentation pipeline built on Azure (Blob Storage, Data Factory, Azure ML, Batch Endpoint). Includes end-to-end data engineering, feature engineering, K-Means model train…

    Python

  5. azure-serverless-invoice-extraction azure-serverless-invoice-extraction Public

    Serverless invoice extraction API using Azure Document Intelligence and Azure Functions. Upload a PDF invoice and receive normalized JSON output including line items, totals, dates, and vendor deta…

    Python

  6. portfolio-site portfolio-site Public

    AI Engineer / Cloud-AI Developer portfolio featuring ML, Azure, FastAPI, and RAG projects.

    HTML