S-01
Ask-your-documents assistant
An AI assistant that answers questions from your company's own files, so staff and customers stop searching.
RAG, LangChain, ChromaDB, FAISS
Ask about thisOpen to full-time roles and freelance projects
I build AI that reads documents and understands images.
I'm Ahmed Ehab, an AI engineer in Cairo. I take a client's problem and turn it into a working system: I design it, build it, test it, and keep it running in production.
Recent work: assistants that answer questions from a company's own documents, cameras that spot objects live on construction sites, and software that reads medical scans.
What I can build for your business
Six kinds of project I have delivered or taught. Pick the closest one and ask, or describe your own.
S-02
Live camera detection
Cameras that spot people, vehicles, or equipment as it happens and send the result to your system. Built for construction-tech clients.
YOLOv8/v10, FastAPI, Docker
Ask about thisS-03
AI workflow automation
Connect your tools so repetitive work, like sorting requests or filling in records, runs by itself and asks a person only when it needs to.
n8n, tool calling, Pydantic
Ask about thisS-04
Case and document management
A web tool for your team to track cases and files in one place. Delivered for a law firm.
FastAPI, SQL, Docker
Ask about thisS-05
Medical and scientific image analysis
Models that read slides and scans, such as pathology images and brain scans, to support the experts who decide.
PyTorch, OpenCV, scikit-learn
Ask about thisS-06
AI and Python training for your team
Hands-on courses from first steps in Python to machine learning. I have taught 500+ students and MSc classes.
Python, machine learning, FlutterFlow
Ask about thisHow a project runs
- 1
You tell me the problem
One call or email. I ask what you need, who will use it, and how you will know it works.
- 2
I plan it in small steps
I turn it into short sprints with clear delivery targets you can measure.
- 3
I build, test, and run it
I design it, build it, test it, and deploy it, so it keeps working in production.
What I do
I build AI that works inside real businesses: assistants that answer questions from a company's own documents, and the web services that put them in front of users. I own the whole job, from understanding what the client needs, to designing the system, to measuring whether it actually works.
Before language models I worked on computer vision and medical data: analyzing huge pathology slides, detecting early signs of Alzheimer's from brain scans, and running object-detection cameras in real time for construction clients. That is why I care about what the data looks like, not just what the model says about it.
I have shipped in legal and healthcare, where "mostly right" is not good enough. I have also led teams of different skills and mentored junior engineers.
Experience
-
June 2025 – present
AI Engineer & Product Owner LOCTech, Saudi Arabia, remote
- Own the AI product roadmap end to end: turn vague client requirements into scoped sprints, architecture decisions, and measurable delivery targets.
- Built and deployed production computer-vision pipelines (YOLOv8/v10, FastAPI) that run real-time detection for construction-tech clients.
- Delivered client-facing products by combining AI-assisted development with reusable service patterns, including a case-management tool for a law firm.
-
July – September 2025
Machine Learning Researcher Intern Nile University, Egypt, hybrid
- Built an end-to-end machine-learning pipeline for diagnosing chronic kidney failure: data preparation, model selection, and evaluation.
-
June – September 2025
Machine Learning & Bioinformatics Instructor Metastatic ME, Egypt, remote
- Taught MSc students data analysis, machine learning, and bioinformatics, breaking hard material into steps they could finish.
-
September – November 2024
Coding Instructor Rocket Academy, Egypt, remote
- Delivered mobile-app development training (FlutterFlow) and helped design the curriculum.
-
March – September 2024
Coding Instructor iSchool, Egypt, hybrid
- Taught 500+ students Python, computer-science basics, AI, and game development, as part of the DEMI project led by Egypt's Ministry of Communications and Information Technology.
-
2021 – 2025
BSc Computational Biology & Genomics Zewail City of Science and Technology
- Specialized in computer vision. GPA 3.26 out of 4.0.
Selected work
Open a row for the details.
-
Cameras that detect objects live. YOLOv8/v10 models behind a FastAPI service, packaged in Docker, for construction-tech clients.
- Running in production with versioned models and fast response times.
- I owned it from the client's requirements through architecture to evaluation.
Python, Ultralytics, FastAPI, Docker, CUDA
-
A tool a law firm's staff use to track and manage their cases, scoped with the client and delivered fast by reusing service patterns from earlier products.
- Worked out requirements directly with the client, in a regulated legal setting.
- Reused service patterns from earlier products to deliver faster.
Python, FastAPI, SQL, Docker
-
A decision-support classifier that reads gigapixel pathology slides, trained without labeling every region by hand.
- Prepared the slides: cut them into patches, separated tissue from background, normalized color, and augmented the data.
- Extracted features with ResNet18, ResNet50, VGG16, and VGG19, and combined them with multiple-instance learning.
- Trained and tuned SVM, logistic regression, decision tree, random forest, KNN, and naïve Bayes classifiers.
Python, PyTorch, scikit-learn, NumPy, CUDA, TIA-Toolbox
-
Machine learning on brain-scan measurements to flag early Alzheimer's.
- Extracted shape and texture measurements from scans with PyRadiomics.
- Normalized the features, removed highly correlated ones, and encoded the labels.
- Compared SVM, logistic regression, decision tree, random forest, and KNN on accuracy, precision, and F1.
Python, PyRadiomics, SimpleITK, scikit-learn, pandas, seaborn
-
A desktop app for clinicians to search disease data collected from DisGeNET, with built-in DNA and protein conversion.
- Stored the collected disease and biology data in a local SQLite database.
- Built the search and the RNA to DNA to protein conversion with Biopython.
- Designed the interface for clinicians with Tkinter and CustomTkinter.
Python, SQLite, Biopython, CustomTkinter
Skills
AI assistants and language models
LangChain, RAG pipelines, n8n, tool and function calling, structured outputs with Pydantic
Search over documents
ChromaDB, FAISS
Using and hosting models
OpenAI SDK, OpenRouter, Ollama for open-weight and local deployment
Software engineering
Python, FastAPI, REST API design, C++, OOP, testing and debugging; familiar with TypeScript
Deployment and infrastructure
Docker, Linux, Git and GitHub, CUDA; familiar with AWS
Data
SQLite, SQL data modeling, NumPy, pandas, Matplotlib and seaborn
Machine learning and computer vision
Deep learning, scikit-learn, OpenCV, Ultralytics YOLOv8/v10, image segmentation, multiple-instance learning
Coding with AI agents
Claude Code, Codex, MCP, plugins, skills
Beyond the code
Teaching. I have taught more than 500 students Python, computer science, AI, and game development through Egypt's DEMI program, trained MSc students in machine learning and bioinformatics, and built mobile-app courses.
Speaking. At Dakahlia STEM School I coached a TED-Ed team of fifteen in public speaking and gave a TEDx-style talk, "The Happiness Paradox."
Laith. Since 2022 I have run a YouTube channel that helps high-school students get into competitive university programs. Watch on YouTube