Available now

AI Engineer who takes systems from business need to production.

Portrait of Naim Makhlouta

I build AI agents, automation pipelines and software products, and I stay close to the people who use them.

Claude CodeLangGraphn8nRAGMCPPyTorchTensorFlowSparkReactNode.jsFastAPIFirebaseDockerPower BI
70–80% lower instruction token cost in Ops Agent 216 prospects enriched and scored in production 1,064 automated tests in Clinetta 80+ solar installations in the data pipeline

How I work

The same three steps, whether the project is an agent, a pipeline or a product.

Step 1

Understand the need

I start with the people and the process: what it costs today, and what would change if it worked. Requirements, KPIs and business cases come before code.

Clinetta requirements, solar market study
Step 2

Build the system

Agents, pipelines and interfaces, with a clear line between what AI judges and what fixed rules calculate. Every claim should trace back to a source.

Ops Agent, CH Lead Generator
Step 3

Take it to production

Deployment, monitoring, guardrails and real measurement, so the system keeps working after it ships and the results can be checked.

Atlas, B2B Lead Scoring Agent

Selected work

All projects

16 projects across work and university. Filter by what interests you.

The Ops Agent's six categories of infrastructure around Claude Code

Ops Agent

A harness I developed that turns an AI coding runtime into an autonomous operational agent, run entirely from plain-language files.

70–80% lower instruction-loading token cost
Production Read
Teaser for one lead, with its roof, a panel layout sketch and estimated savings

CH Lead Generator

Pick an area on a map and get a ranked list of real buildings, each with a draft proposal.

10 automated steps per site
Production Read
Clinetta weekly agenda with appointments coloured by status

Clinetta

One shared clinic system that replaces a paper agenda and Word patient files.

1,064 automated tests
Production Read
Workflow of the research agent from a competitor name to a battlecard, and of the app it deploys and monitors

Atlas

A competitor analysis agent and AI strategic analysis platform. Type a competitor's name and get a sourced battlecard, threat alerts and ranked strategic gaps.

12 research steps per competitor
Production Read

B2B Lead Scoring Agent

Turns a company name in Notion into an enriched, scored partner candidate with a ready-to-read brief.

216 prospects enriched and scored in production
Production Read
The SOIA assistant answering a question with a retrieved diagram and sources

SOIA Multimodal RAG

A course assistant that answers from slides and diagrams, shows the figure, and cites the exact page.

2 modalities retrieved: text and images
Academic Read
SHAP chart of the most influential clinical variables

MVTE Recurrence Prediction

An explainable model that helps doctors estimate whether a patient's blood clot disease will come back.

0.93 weighted F1 on the test set
Academic Read
Huawei FusionSolar app screens showing energy flow, energy management and module monitoring

Solar Analytics & Upsell Agent

Turns raw solar monitoring data into reports and justified product recommendations for each client.

80+ solar installations in the pipeline
Production Read
A distributor public catalogue of solar panels

Supplier Price Sync

Keeps negotiated prices current across suppliers and accounts, and shows exactly what failed to update.

4 suppliers on 4 different platforms
Production Read
Odoo logo

Odoo Dev Kit

A Claude Code plugin that lets developers build on Odoo without the AI inventing APIs.

13 durable concepts in the guide
Internal tool Read
Power BI dashboard of solar installations across France

French Solar Market Study

The Power BI business case that won me the internship, turning 23,368 installations into a two-speed marketing strategy.

23,368 installations analysed
Business case Read

Accident Report LLM Extractor

Turns free-form accident reports into structured JSON, and benchmarks three LLMs on the task.

3 models compared
Academic Read
Correlation matrix on the moderately balanced subset

Spark Fraud Detection

A distributed ML pipeline that hunts rare fraud in 284,807 transactions, where only 0.17% are fraudulent.

284,807 transactions processed
Academic Read
Chart of accuracy against model size for FP32 and INT8

CNN Compression

Makes a ResNet-18 about 4× smaller and 2× faster, with almost no loss of accuracy.

44.9 → 11.4 MB model size after quantization
Academic Read
A dim scene after denoising

Image Denoising Autoencoder

A convolutional autoencoder trained on real camera sensor noise, then tested on a different sensor.

32.4 dB mean PSNR on the test images
Academic Read
Red motion arrows from Horn-Schunck optical flow on people moving in a shopping centre

Optical Flow Motion Tracker

A real-time webcam demonstrator that detects and tracks moving objects, built on the classic Horn–Schunck method.

Real time on a live webcam feed
Academic Read

Also explored: Grover's quantum search algorithm in Qiskit, with single-solution, multi-solution and subset-sum applications.

Experience

Mar 2026 – Sept 2026

AI & Data Engineer, Solarock

Final-year engineering internship at a French solar company

  • Designed and deployed a multi-agent architecture to automate high-repetition business processes.
  • Built data pipelines on solar monitoring APIs, with cleaning and normalisation across 80+ installations.
  • Turned complex energy data into decision tools for non-technical teams, and took prototypes through to production.
May 2025 – Aug 2025

AI Agent Developer Intern, Webspot

Agents and automation on n8n

  • Built and deployed multi-channel agents on WhatsApp, Telegram and web landing pages, connected to dashboards.
  • Handled data scraping, cleaning, prompt engineering and workflow design, linking agents to external APIs.

Training & speaking

Workshops and talks, including with the AI Club at the Lebanese University.

Skills

AI & Agents

Claude / Anthropic · n8n · LangGraph · LangChain · Prompt engineering · Agent architecture · MCP · RAG · LLMs · NLP · Hugging Face

See it in Ops Agent →

Deep Learning & ML

PyTorch · TensorFlow · Computer vision · Machine learning · Spark / PySpark · XGBoost · SHAP & LIME

See it in MVTE Prediction →

Data & Analytics

Python · Power BI · Power Query · Data pipelines · REST / GraphQL APIs · Data scraping · Excel

See it in Solar Analytics →

Software

React · Node.js · Firebase / Firestore · FastAPI · Docker · C# · Java · Matlab · Git

See it in Clinetta →

Product & Management

Product strategy · Requirements & MoSCoW · UX/UI design · Market research · Agile / Scrum · Roadmapping · Go-to-market · Notion

See it in Clinetta →

Business & Ops

Workflow automation · B2B lead generation · Competitive intelligence · Business analysis · KPI design · HubSpot · Odoo

See it in Market Study →

Education & certificates

Degrees

Engineering Degree in Observation Systems & Artificial Intelligence ENSTA (Brest Campus) · Aug 2024 – Sept 2026 Final-year project: Ops Agent, defended September 2026.
Engineering Degree in Electrical and Electronic Engineering Lebanese University, Faculty of Engineering (ULFG1) · Sept 2021 – Sept 2026 Specialization in telecommunications and information technology.

Certificates and awards

Microsoft AI Product Manager, Professional Certificate Microsoft / Coursera · Jul 2026 Enterprise product management · Market research and competitive analysis · Product strategy and roadmapping · Product design and UX/UI · Product launch and post-launch management
MOOC Project Management (GDP) Centrale Lille · 2024 Project management, Agile with Scrum, and web tools for project execution
Hult Prize, 2nd place 2021–2022 Green Cycle: reusing food waste to create sustainable products, reducing toxic waste and generating jobs