Portrait of Emna Tounssi Open to full-time roles and freelance projects, remote or in Tunis

Data scientist and AI engineer · ENIT graduate, 2026

Emna Tounssi

I build AI assistants, predictive models and computer-vision tools that work on real data.

I measure honestly what my models are worth before showing them.

databot · “Olist e-commerce” workspace
DataBot on a PostgreSQL database it is discovering: a plain-language question, then the answer and its chart.Watch the full demo →
end-to-end projects
5
industry internships
2
video demos
3
ENIT graduate
2026

About

Honestly evaluated models, shipped in tools people use

Modelling and data science engineer, graduated from the National Engineering School of Tunis in 2026. I like complete projects: start from raw data, build a model or an agent, evaluate it on data it has never seen, then ship it in a tool someone actually uses.

My projects span classical machine learning, deep learning for vision, signal processing and generative AI: agents, RAG and LLM-as-judge evaluation.

  • Machine learning and deep learningClassification, anomaly detection, vision, signals
  • Generative AI and agentsLangGraph agents, RAG, LLM-as-judge evaluation
  • From data to productAPIs, web apps, Docker, automated tests

Services

What I can build for you

Each service is backed by projects you can open, with their measured results and limits.

Machine learning and deep learning models

Prediction, classification, forecasting and anomaly detection on your data, for retail, industry, health or finance.

Projects: DataBot, ThreatLens, EEG

AI solutions with large language models

AI assistants that answer from your documents or data (RAG) and agents that automate multi-step tasks.

Projects: Explain My Model, DataBot

Computer vision

Detection and classification on images and video, from data cleaning to real-time inference.

Projects: Facial emotion recognition

Projects

Five end-to-end projects

Each project shows its measured results, its method and its limits.

Personal and academic projects, with demos or results

2 video demos

Personal project · 2025 to 2026

DataBot: your AI-powered data science assistant

Ask questions about your business data in plain language and get the answer with its chart, or run a full data science project together, approving each step, with everything delivered as a notebook and a PDF report.

An AI assistant that connects to databases and files, writes and runs the code, builds and evaluates models. It follows CRISP-DM and only moves to the next phase once the user approves. Ready for public deployment: open accounts, each user's own AI key, isolated code.

Subscriptions for the same calls
+40%
AUC on future campaigns
0.65
Automated tests
≈ 330
  • GPT-5.1
  • GPT-5.4
  • LangChain
  • LangGraph
  • FastAPI
  • React
  • DuckDB
  • Docker
View project
Video demo

Personal project · computer vision · 2026

Real-time facial emotion recognition

Recognises the emotion on each face in a video (happiness, surprise, anger…) and shows how sure it is, faster than the video plays.

A pre-trained ResNet-18 recognises 7 emotions on every face in a video, in real time. I first removed 7,976 doubtful images, including 1,916 copies shared between training and test, then measured on a clean test set: 82.7% accuracy.

Accuracy, clean test set
82.7%
Right emotion in the top 2
95.5%
Speed on CPU only
49 fps
  • PyTorch
  • ResNet-18
  • transfer learning
  • OpenCV
  • YuNet
  • scikit-learn
View project
Results per patient

Second-year engineering project, ENIT, in a pair · 2025

Epileptic seizure detection from EEG signals

Automatically spots epileptic seizures in brain-signal (EEG) recordings.

One model per patient on the CHB-MIT database: filtering, signal features, channel selection with Boruta and a threshold tuned not to miss seizures. 31 of 32 seizures detected.

Recall
95.3%
Precision
99.5%
Seizures detected
31 / 32
  • Python
  • MNE
  • scikit-learn
  • imbalanced-learn
  • Random Forest
  • Boruta
  • wavelets
View project

Industry projects: case studies, code and data confidential

Case studyPwC Tunisia · final-year engineering project · February to July 2026

Explain My Model: automatic documentation of credit risk models

Reads the SAS, Python and R code of a bank's credit risk models, even code built on SAS Risk Dimensions, a proprietary engine with no public documentation, and writes their technical and regulatory documentation, checked automatically and then approved by an expert.

Final-year project at PwC: eight AI agents read the SAS, Python and R code of credit risk models and write their IFRS 9 and Basel III documentation. Automatic checks, an LLM judge and expert review: 0.96 faithfulness to code.

Faithfulness to code, 46 evaluations
0.96
Lines of code covered
100%
Success criteria met
4 / 5
  • LangGraph
  • LangChain
  • RAG (BGE-M3, FAISS)
  • DeepEval
  • Llama 3.3 70B
  • Flask
  • SQLite
  • Playwright
  • ReportLab
View project

Case studyNavitrends · remote engineering internship · July to August 2025

ThreatLens: detecting attacks in web server logs

Watches a website's traffic and flags suspicious visitors (vulnerability scans, password attacks, bots), showing where they come from and sending an alert by email.

Unsupervised detection of scans, attacks and bots in 1.83 GB of web logs. Isolation Forest scores each address every 5 minutes; the ThreatLens app shows a map and sends PDF alerts. F1 of 0.92 on a simulated test set.

Logs analysed (92 files)
1.83 GB
F1, injected anomalies
0.92
Interface response time
< 200 ms
  • Python
  • scikit-learn
  • Isolation Forest
  • DBSCAN
  • t-SNE
  • Flask
  • SQLite
  • GeoLite2
  • Leaflet
  • ReportLab
View project

Approach

How I work

01

Frame before coding

I start by setting what matters and how to measure it: missing an epileptic seizure costs more than a false alarm, so recall comes first; in my final-year project, five measurable success criteria were set before the first line of code.

Example: Explain My Model →

02

Check the data

Before modelling, I look for what would distort the result: 1,916 images shared by training and test removed, customers counted twice, incomplete months, amounts inflated by joins.

Example: Emotions →

03

Evaluate without cheating

An isolated test set used only once, real time order when it matters, comparison with reference models, confidence intervals. Settings are chosen on validation, never on the test set.

Example: DataBot →

04

Ship it, limits included

I go all the way to the tool people use: a dashboard with alerts, a platform for experts, PDF reports, a notebook. Every deliverable says where it can be trusted and where it cannot.

Example: Anomalies →

Experience

Experience and education

  1. February to July 2026 · Tunis

    AI Engineering Intern, PwC Tunisia

    Final-year engineering project in Risk Services Maghreb: a multi-agent generative AI platform that reads the code of credit risk models and writes their IFRS 9 and Basel III documentation, checked automatically then approved by an expert. View project.

  2. July to August 2025 · remote

    Data Science Engineering Intern, Navitrends

    Unsupervised attack detection in 1.83 GB of web logs, and ThreatLens, a monitoring application with a map and PDF email alerts. View project.

Education

  • National Engineering School of Tunis (ENIT)Engineering degree in modelling and data science, 2023 to 2026
  • Faculty of Sciences of TunisBachelor's in mathematics and computer science, 2020 to 2023, with honours, ranked first in class

Certification

AI Engineer for Data Scientists Associate, DataCamp, 11 December 2025. View the certificate

Skills

Tools, linked to the projects

Machine learning

  • scikit-learn
  • Random Forest
  • Isolation Forest
  • DBSCAN
  • t-SNE
  • Boruta
  • Time-based validation
  • Anomaly detection

Used in: DataBot, EEG, Anomalies

Deep learning and vision

  • PyTorch
  • ResNet
  • Transfer learning
  • CNN
  • TensorFlow
  • Keras
  • OpenCV
  • Data augmentation

Used in: Emotions

Generative AI and agents

  • LLMs
  • Multi-agent systems
  • LangChain
  • LangGraph
  • RAG
  • FAISS
  • BGE-M3
  • DeepEval
  • LLM-as-judge
  • Prompt engineering

Used in: DataBot, Explain My Model

Signal processing

  • MNE
  • Filtering
  • Wavelets
  • Entropies
  • Spectral analysis

Used in: EEG

Data and evaluation

  • Python
  • pandas
  • SQL
  • PostgreSQL
  • MySQL
  • SQLite
  • DuckDB
  • Matplotlib
  • Bootstrap and confidence intervals

Used in: DataBot, Emotions, Anomalies

Software engineering

  • FastAPI
  • Flask
  • React
  • Docker
  • Automated testing
  • Authentication and roles
  • PDF reports (ReportLab)
  • Git

Used in: DataBot, Explain My Model, Anomalies

Domain knowledge

  • Credit risk: IFRS 9, Basel III
  • Cybersecurity: web logs
  • Health: EEG signals
  • E-commerce and bank marketing

Used in: Explain My Model, Anomalies, EEG, DataBot

Languages

  • Arabic: native
  • French: full professional proficiency
  • English: professional working proficiency

Contact

A role or a project in data science, machine learning or generative AI? Let's talk.

I am open to full-time roles and freelance projects, remote or in Tunis. The easiest way is to email me: I reply quickly.

emnatounssi@gmail.com