Mosab Ahmed profile picture

Hello, I'm

Mosab Ahmed

AI Engineer — Security & Governance-Focused

Building AI systems with security, auditability, and deployment discipline.

AI Security RAG Systems FastAPI Governance Evidence

Get To Know More

About Mosab Ahmed

My path into AI did not start with AI — it started with circuits. Electronics Engineering gave me a systems-level instinct for how technology works under the hood, which became the right foundation for building and governing AI systems.

Today I work close to critical systems, infrastructure risk, and operational accountability. That context shaped my focus: AI security engineering, retrieval systems, model-serving APIs, evaluation workflows, and governance evidence that can survive real review.

01

AI Security

Prompt guardrails, access-controlled retrieval, and safety evaluation.

02

Production ML

Model training, validation, API serving, testing, and deployment structure.

03

Governance Evidence

Model cards, risk registers, failure analysis, data lineage, and audit notes.

Core Technical

Focus Areas

I focus on the parts of AI engineering that matter in real deployment: reliable models, safe serving, measurable retrieval, and documentation that supports governance and audit.

Machine learning engineering icon

ML Engineering

Preprocessing, validation, model comparison, failure analysis, and model persistence for NLP, tabular, and security classification tasks.

LLM and RAG systems icon

LLM & RAG Systems

Chunking, embeddings, vector search, hybrid retrieval, reranking, source traceability, and retrieval evaluation workflows.

AI security and governance icon

AI Security & Governance

Prompt safety, access control, model cards, risk registers, data lineage, failure analysis, and audit-ready documentation.

MLOps and API serving icon

MLOps & API Serving

FastAPI, Docker, health checks, automated tests, structured logging, CI/CD-ready layouts, and deployment discipline.

AI Assurance Case Studies

Synthetic case study

Assessing a Vendor’s Video Analytics Claim

A hypothetical vendor claims 95% person detection without providing evidence for the intended operating conditions.

Read case study

Evidence gap. The claim provides no definition of a detection, sample counts, test conditions, or software version.

Proposed verification. Request the test report and agree on the acceptance criteria before a witnessed demonstration. Record missed events, false alarms, and alert delay. Check how operators verify alerts and learn when the feature is unavailable.

Recommendation. Hold technical acceptance of the feature until the evidence and test results support its intended use.

Browse Through My

Selected AI Engineering Projects

A focused set of production-shaped AI projects covering AI security, retrieval systems, model serving, evaluation, and governance evidence.

Governance RAG / LLM Systems

Shipped

RAG over NIST AI RMF

A local retrieval-augmented generation system over the NIST AI Risk Management Framework with source traceability.

LangChainChromasentence-transformersOllamaStreamlit
Evidence

Document chunking, top-k retrieval, source citations, traceability requirement, limitation notes.

Secure RAG / Authorization

In Progress

Access-Controlled RAG

A retrieval system where documents and retrieved context are governed by user roles and authorization boundaries.

LlamaIndexQdrantPythonlocal LLMmetadata filters
Evidence

Role-aware retrieval, controlled context access, authorization matrix, access-control evidence.

Production RAG / Evaluation

In Progress

Production RAG with Hybrid Search

A more advanced RAG system moving beyond naive retrieval into hybrid search, reranking, and evaluation.

Pythonhybrid retrievalrerankingvector searchevaluation
Evidence

Retrieval evaluation, ranking comparison, failure inspection, retrieval-quality notes.

MLOps / API Deployment

Shipped

Containerized Sentiment API

A sentiment-analysis model refactored from notebook form into a tested FastAPI service packaged with Docker.

FastAPIDockerPydanticpytestTransformers
Evidence

Liveness checks, readiness checks, structured project layout, automated tests, one-page model card.

LLM Infrastructure Study

Shipped

Local vs Hosted LLM Benchmark

A practical benchmark comparing local and hosted LLM usage across latency, throughput, prompt length, and deployment trade-offs.

PythonOllamaHosted APIsDocker Compose

Transformer Internals

Learning Lab

GPT Architecture From Scratch

An educational PyTorch implementation used to understand GPT-style architecture blocks, embeddings, and attention mechanics.

PythonPyTorchTransformer blocks

Explore My

Other Platforms

Get In Touch

Contact Me

Contact Information

Name

Mosab Ahmed

Location

Doha, Qatar

LinkedIn LinkedIn Profile