Zaid Diab
AI workflows for real business problems — and the software to run them.
Computer Science graduate (German-Jordanian University, with an exchange semester at Hochschule Trier). Currently an intern at Porsche Digital, building AI-driven prototypes, LLM routing systems, agentic RAG workflows, CI/CD onto embedded Linux, OTA pipelines, and real-time perception on edge hardware.
// status
What I'm doing now
// selected work
Things I've shipped
A few projects that show the range: agentic RAG, LLM routing, custom AI automation, software systems, DevOps, backend, and Linux.
- in progressMay 2026 to present
EFQM/RADAR AI Report Analyzer
A local-first, multi-agent RAG pipeline for the first-pass desk assessment of EFQM-based organizational self-assessment reports. It retrieves assessment guidance, links findings to source evidence, flags gaps and conflicts, and produces structured draft feedback for human review.
Read case study - shipped2025 — 2026
LLM Routing System
An internal on-device LLM routing layer that classifies each prompt by task type and complexity before selecting a local model or cloud provider. My operational estimate was that roughly 65 percent of requests stayed local, reducing cloud AI spend by about 45 percent.
Read case study - shipped2025 to 2026
Vehicle Software Infrastructure
Built and maintained CI/CD pipelines for Dockerized C++ and Python backend services on embedded Linux across ARM and x86 targets. I taught myself Rust on the job and implemented a REST-based OTA update mechanism on three test vehicles with automated version checks, fallback logic, health monitoring, and service orchestration.
Read case study - shipped2025 to 2026
Edge AI Computer Vision Prototype
Real-time object detection prototype using GStreamer and YOLO on embedded ARM and x86 hardware. The modular pipeline separates preprocessing, inference, post-processing, and visualization, then produces visual overlays and structured detection metadata for downstream feedback experiments.
Read case study
// toolkit
A focused, production-tested stack
Depth over breadth — the tools I reach for when something has to ship and keep running.
01
AI / ML & Agents
RAG pipelines, LLM agents, local inference, LLM routing, perception, and classical ML.
- RAG pipelines
- LLM agents
- Local LLM inference
- LLM routing
- YOLO
- Random Forest
- Computer Vision
- LiDAR
- GStreamer
- SMOTE
02
Backend & Systems
Services, APIs, and the code that runs underneath.
- Python
- C++
- Rust
- C#
- ASP.NET Core
- REST APIs
- FastAPI
03
DevOps & Platforms
Shipping it — and keeping it alive in production.
- Docker
- CI/CD pipelines
- Linux
- systemd
- Shell scripting
- Git
04
Frontend / Mobile
Interfaces and cross-platform mobile apps.
- Flutter
- React.js
- Kotlin
05
Databases
Where the state lives.
- MySQL
- Firebase Realtime Database
- SQLite
// let's talk
Looking for an AI engineer who ships production systems?
Open to AI engineering, AI agent, RAG, LLM systems, software, DevOps, backend, and Linux roles across Europe and the Middle East from September 2026. Also open to freelance AI automation and custom software projects.