Engineering a Production AI Assistant: Securing a Paid LLM Endpoint (Part 2/3)
- llm
- artificial-intelligence
- security
- redis
- optimization
Hi, I am Jawher Ennaceur - AI & Software Engineer
AI & Software Engineer
I build AI systems that get used, not just demoed.
I'm an AI & Software Engineer specializing in LLM-powered systems: RAG pipelines, multi-agent workflows, and knowledge graphs, deployed for real business use cases. Based in Tunisia. I care about shipping things that actually work in production, not just proof-of-concepts.
Professional Experience
CLASS QUIZ
Sousse, TunisiaJul 2026 – Present
AI Engineer
Full-time- Designing and building an automated exam correction system that replaces a manual workflow of printed exams, handwritten answers and photos sent via WhatsApp.
- Designed a marker-based page-recovery system: markers in the four corners of every page encode the exam ID and page number, and are detected in student photos to identify, crop and rectify each page from noisy backgrounds.
- Built an OCR (Google Vision) and exercise-segmentation pipeline with an 8-category Gemini classifier and a dedicated extraction prompt per exercise type, structuring blank exams (content, answer key, marking scheme) into PostgreSQL.
- Extract students' handwritten answers with the same pipeline, then retrieve the matching exam structure from PostgreSQL using the decoded markers.
- Implemented RAG-grounded automated grading with Gemini, evaluating each answer against the original exercise, correct answer, marking scheme and curriculum knowledge from a dedicated vector database of educational books.
DELOITTE
Tunis, TunisiaFeb 2026 – Jun 2026
AI Engineer
Internship- Built an AI-powered insurance sales assistant from requirements analysis to deployment, helping agents progressively qualify customer needs, check product eligibility and generate personalized recommendations.
- Designed a multi-agent system with LangChain and LangGraph, coordinating five specialized agents through shared state, with persistent workflow state and automatic recovery via LangGraph checkpointing on PostgreSQL.
- Combined LLM-based reasoning with a deterministic business-rules engine that enforces eligibility and commercial constraints, so decisions follow explicit, reviewable rules.
- Built a Graph RAG pipeline on Neo4j that turns unstructured documents into a knowledge graph through OCR, semantic processing and LLM-based structured extraction.
- Designed prompt-driven agents that generate tailored product recommendations and sales arguments; in tests, they surfaced 60%+ of previously missed cross-selling opportunities.
- Benchmarked proprietary and open-source LLMs on cost, performance and latency to choose the models for the solution.
- Developed the FastAPI backend and React/TypeScript frontend, with JWT authentication, role-based access control, agency-level data isolation and role-specific Metabase dashboards.
CLASS QUIZ
Sousse, TunisiaAug 2025 – Feb 2026
AI Engineer
Part-time- Took the educational chatbot from MVP to production: evaluated it, containerized it with Docker and deployed it on a server.
- Integrated the chatbot with both the web and Unity versions of the application through Socket.IO, so the app is not blocked while it waits for an answer.
- Built a book summarization system for the official encrypted school manuals: it detects the table of contents, extracts each chapter's title and start and end pages, and splits the book by those page ranges.
- Used Gemini to produce a summary, keywords and targeted skills for each chapter; each summary is stored as a chunk (long chapters split in two) with the skills and keywords as metadata, in the vector database that serves as the chatbot's RAG knowledge base.
- Replaced a largely manual content-preparation process, reducing preparation time by about 70%.
Jun 2025 – Jul 2025
AI Engineer
Internship- Designed and built the MVP of a RAG-based educational chatbot (LangChain, OpenAI API, ChromaDB) that assists children while they solve exercises, using the current exercise, its correct answer, conversation history in PostgreSQL and content from official Tunisian curriculum books. Tested the MVP on a knowledge base of 10 chapter summaries.
- Built a contextualization step that rewrites each child's query using conversation and exercise context before retrieval.
- Implemented dynamic prompts with separate strategies for child and parent users on the same pipeline.
- Added a modular linguistic-correction layer that normalizes spelling and grammar errors in children's input, reducing input errors by about 40% on the messages I tested.
- Implemented voice interaction as an interface layer (speech-to-text, chatbot, text-to-speech) without changing the core text pipeline.
- Converted Unity-oriented JSON exercise data into Markdown with Python scripts so it could be reused as AI context.
DATA SCALE
Tunis, TunisiaJul 2024 – Aug 2024
Machine Learning Engineer Intern
Internship- Automated client onboarding for a SaaS purchase-intent prediction platform for e-commerce, building a preprocessing pipeline that adapts each new client's raw data (shared and site-specific features) to the existing ML workflow.
- Implemented missing-value imputation (forward-fill, median), target encoding for categorical features, and automated data cleaning and transformation.
- Designed an automated transfer-learning pipeline for a LightGBM model, pre-trained on general data and fine-tuned per new client, replacing manual per-client retraining and making onboarding reusable.
- Developed a RAG-based website chatbot with Google Agent Builder, backed by a categorized knowledge base, and integrated a booking API so users can reserve services directly in the conversation.
- Created Flask APIs to serve trained ML models and automate backend data-processing services.
AI & Data Projects
RAG Chatbot Assistant
Ask questions about your own documents and get short, grounded answers. Files are chunked and embedded into a vector store, and a Gemini model answers using only the retrieved passages and the conversation so far.
- RAG
- LLM Applications
- LangChain
- FastAPI
- Vector Databases
- NLP
Product Advisor — LLM Assistant
This project combines a large language model with structured product data to build a conversational shopping assistant. It uses intent classification and entity extraction to separate recommendation requests, product comparisons and general questions. Fuzzy product matching resolves product names in comparisons, and prompt-based LLM responses turn the matched specifications into practical advice on price, RAM, storage, camera and battery.
- LLMs
- LangChain
- Prompt Engineering
- Natural Language Processing
- Intent Classification
- Fuzzy Matching
Genetic Algorithm — Defense Scheduling Optimization
This project uses a genetic algorithm to automate the scheduling of academic defenses. It reads students, supervisors and rooms from Excel files, builds conflict-free candidate schedules, and provides selection, crossover and mutation operators to improve them. A custom evaluation function penalizes resource conflicts and scores how compactly each professor's sessions are grouped across days and time slots.
- Genetic Algorithms
- Optimization
- Python
- Constraint Satisfaction
- Scheduling
- Data Processing
Hand Sign Classifier
The notebook loads a class-per-folder image dataset (133 training and 32 validation images), applies random augmentation, and trains a small classification head on top of a frozen MobileNetV2 for 20 epochs. It plots training and validation accuracy and loss, saves the model as an HDF5 file, and passes a webcam frame captured in Colab through the model to get a two-class softmax output. Validation accuracy reaches 1.0, but on a 32-image split that is augmented like the training data, so it is a sanity check and not a measure of real-world accuracy.
- Transfer Learning
- Image Classification
- Data Augmentation
- TensorFlow And Keras
- Computer Vision
Face Verification with a Siamese Network
Instead of classifying faces into fixed identities, this project learns a face embedding and compares two images by the distance between their embeddings, an approach designed to verify a face against a single reference photo without retraining a classifier. Built with TensorFlow and a custom training loop.
- Deep Learning
- Computer Vision
- Siamese Networks
- Data Augmentation
- TensorFlow
Billing Fraud Detection
The notebook merges client records with invoice history, cleans and encodes the data, and undersamples the majority class to a 3:1 ratio. It then trains and compares three models on a stratified 75/25 split. All three reach 100% accuracy, because the label column was left among the input features, so the notebook demonstrates the full pipeline but does not yet measure real detection performance.
- Fraud Detection
- Feature Engineering
- Imbalanced Data Handling
- Scikit-Learn
- Neural Networks
- Exploratory Data Analysis
My Skills
AI & Machine Learning
- Machine Learning
- Deep Learning
- Computer Vision
- NLP
- LLM
- RAG
- Graph RAG
- Agentic AI
- Multi-Agent Systems
- Prompt Engineering
- Transfer Learning
Data
- Data Science
- Data Analysis
- BI
- ETL
- SQL
- NoSQL
Frameworks & Libraries
- LangChain
- LangGraph
- Flask
- FastAPI
- PyTorch
- TensorFlow
- Scikit-learn
Cloud & DevOps
- Docker
- Azure
- GCP
- MLOps
Software Engineering
- REST APIs
- Web Development
- Algorithm Design & Analysis
- System Design
- Authentication & Authorization
Programming Languages
- Python
- Java
- JavaScript
- TypeScript
- C++
- C
Tools & Frameworks
LangChain
LangGraph
FastAPI
Docker
Pytorch
GCP
Azure
PostgreSQL
Neo4j
ChromaDB
Academic Journey
Education
Sept. 2023– July 2026
Software Engineering (National Engineering Diploma)
Institution: Higher Institute of Applied Sciences and Technology of Sousse
Sept. 2021– June 2023
Pre-Engineering Cycle – Mathematics, Physics and Computer Science (MPI)
Institution: Higher Institute of Applied Sciences and Technology of Sousse
2017 - 2021
Scientific Baccalaureate
Institution: Eljem high school
Certifications
Nov. 2025
Building LLM Applications With Prompt Engineering
Institution: NVIDIA
March 2025
Generative AI with Diffusion Models
Institution: NVIDIA
April 2023
Deep Learning Specialization
Institution: DeepLearning.AI
Nov. 2022
Machine Learning Specialization
Institution: Stanford University & DeepLearning.AI
Blog & Articles
Engineering a Production AI Assistant: Keeping Answers True to Your Data (Part 1/3)
- llm-large-language-model
- ai-agent
- software-engineering
- rags
- prompt-engineering
CAG in the Real World: Latency, Cost, and Limits Compared to RAG (Part 2/2)
- llm
- retrieval-augmented-gen
- artificial-intelligence
- machine-learning
CAG in the Real World: Architecture of a Preloaded KV Cache System (Part 1/2)
- genai
- python
- machine-learning
- llm
Engineering Agentic AI Systems: What MCP Really Changes for Agents (Part 3/3)
- ai-engineering
- software-engineering
- artificial-intelligence
- llm
- ai-agent
Engineering Agentic AI Systems: Multi-Agent Orchestration with LangGraph (Part 2/3)
- ai-agent
- software-engineering
- artificial-intelligence
- llm
- machine-learning
Community Involvement
NATEG ISSATso Club
- Event Manager:Planned and executed club events from start to finish. Coordinated teams for marketing, organization, and logistics to ensure smooth delivery.
- Board Member:Participated in decision-making processes. Helped set club goals and strategies.
- HR Member:Managed member relations. Resolved conflicts and supported team dynamics.
- AI Instructor:Designed and delivered AI training sessions. Helped over 60 participants grasp AI fundamentals and practical applications.
Tunisian Scout Association
- Wood Badge Holder:Achieved advanced scouting skills and demonstrated commitment to the movement.
- Group Leader:Led scout groups. Organized activities and mentored younger members.
- Trainer:Delivered training sessions to develop skills and build confidence in scouts.
- Team Builder:Promoted teamwork and community values within the association.
Contact Me!
Prefer email? jawherennaceur@gmail.com