Skip to content
ZeyadKhalil

Agentic AI · RAG Pipelines · Computer Vision · LLMs · ML Engineering

ZeyadKhalil

Building production-ready AI systems and intelligent pipelines.

Building agentic AI systems and RAG pipelines that ship to production, including an embeddings-based job-matching copilot with semantic retrieval and full API orchestration, and a real-time LLM data loss prevention platform that reached the Google London hackathon grand final. Skilled across the model lifecycle: PyTorch, deep learning, computer vision, NLP and cloud deployment on GCP and AWS. Currently completing MSc Applied AI at the University of Warwick (WMG) with a computer vision dissertation at Dogtooth Technologies.

AI Assistant

Hi, I'm Zeyad's AI. Ask me about his projects, skills, or experience.

Try asking:

Featured work

Projects

Agentic pipelines, LLM applications, computer vision and full-stack APIs.

All projects
AI Systems · Sensor ML · Industry Research2026

Dogtooth AI Collision Intelligence System

MSc industry dissertation with Dogtooth Technologies. A sensor-driven pipeline that detects harmful infrastructure interactions on autonomous strawberry harvesting robots, reducing downtime without compromising safety.

Python · Sensor ML · Time-series features · Anomaly detection · Severity classification

In progress
Computer Vision · Domain Adaptation · Deep Learning2026

Strawberry Ripeness Detection Under Day-to-Night Domain Shift

Computer vision project tackling performance drop in fruit ripeness classification when lighting shifts from daylight to LED-illuminated polytunnels. Built on the StrawDI_Db1 dataset with a CycleGAN-based domain adaptation pipeline that translates daytime imagery into the night domain for training, evaluated before and after adaptation with accuracy, precision, recall and confusion matrices.

PyTorch · CycleGAN · Domain adaptation · Transfer learning · Model evaluation

Research
LLM Security · Data Loss Prevention · Google London Final2026

PromptGuard AI: Enterprise LLM Data Loss Prevention

Applied AI security platform built during the WMG / Google / NatWest Secure Intelligence Frontier hackathon (advanced to the grand final at Google London). Intercepts prompts sent to public LLMs from the browser and detects sensitive data leakage in real time. Chrome Extension (Manifest V3) for in-browser interception, FastAPI backend on Google Cloud Run for detection and policy enforcement, and a React admin dashboard for analytics and rule configuration.

FastAPI · Cloud Run · Chrome Extension MV3 · LLM classification · React dashboard

Active
Agentic AI · Semantic Search · Full-Stack Product2025

Agentic AI Job Application Copilot

End-to-end automation platform that finds, ranks and helps apply to relevant graduate roles. FastAPI + SQLAlchemy 2 backend with APScheduler-driven Greenhouse scrapers, an embeddings-based semantic matching pipeline that ranks roles against a candidate CV, a Next.js 15 frontend with TanStack Query, and a 28-test suite locking in scraper reliability and matching logic.

FastAPI · Next.js 15 · Embeddings · SQLAlchemy 2 · Pytest suite

Active

Skills

Tools I actually use

Technologies I use across applied AI, software engineering and product work.

AI & Machine Learning

  • PyTorch
  • scikit-learn
  • NumPy
  • pandas
  • SciPy
  • Supervised & unsupervised learning
  • Feature engineering
  • Model evaluation
  • Hyperparameter tuning
  • Data visualisation

Deep Learning, CV & Generative

  • CNN backbones
  • Transfer learning
  • Image classification
  • CycleGAN
  • Generative domain adaptation
  • Distribution shift
  • Augmentation pipelines
  • Grad-CAM

LLMs, RAG & Agentic AI

  • LLM application engineering
  • RAG (BM25 + embeddings)
  • Prompt injection defences
  • DLP for prompts
  • Agentic workflow design
  • Embeddings-based semantic matching
  • Streaming SSE
  • Hybrid regex + LLM detection

Reinforcement Learning & Autonomous Systems

  • MDPs
  • Q-learning
  • DQN
  • Policy gradients
  • Actor-Critic basics
  • PPO basics
  • Continuous-action RL
  • Custom simulation environments
  • TORCS simulator
  • Telemetry / sensor signals
  • Sensor ML
  • Collision classification

Backend, APIs & Data

  • FastAPI
  • Flask
  • SQLAlchemy 2
  • APScheduler
  • REST APIs
  • Pydantic
  • MySQL
  • PostgreSQL
  • SQL design & normalisation
  • ETL & data pipelines
  • Pytest

Frontend & Full Stack

  • Next.js 15 (App Router)
  • React
  • TanStack Query
  • TypeScript
  • Tailwind CSS
  • Chrome Extension Manifest V3
  • AJAX / fetch
  • PHP

Languages & Programming

  • Python
  • TypeScript
  • JavaScript
  • Java
  • C++
  • C#
  • R
  • SQL

Cloud, MLOps & Tooling

  • AWS
  • Google Cloud Platform
  • Google Cloud Run
  • Vercel
  • Git & GitHub
  • Linux command line
  • CI workflows
  • Agile / Scrum
  • Reproducible experiments

Spoken Languages

  • English
  • Italian
  • Arabic
  • French

Contact

Open to AI, machine learning and software engineering opportunities.

I'm interested in roles where I can build production-focused AI systems, computer vision models, LLM applications, data pipelines and full-stack software for real users.