
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Full stack , AI ,MLOps Engineer with 1+ years in Machine Learning Pipelines & Time-Series Forecasting
Full Stack Engineer with hands-on experience in ERP development, backend systems, DevOps/cloud infrastructure, data analysis, and AI-focused engineering. At REF-IT, I have contributed to two ERP projects and am currently working on one active ERP project, where I develop and optimize PHP/Laravel applications, improve database performance, and support business data analysis. Alongside my current position as a Full Stack Engineer, I also focus on AI, with previous experience in CI/CD automation, Kubernetes, Dockerized deployments, monitoring, FastAPI services, and ML-driven telemetry systems. I bring a strong security-by-design mindset, with practical exposure to infrastructure hardening and pfSense firewall configuration
National School of Electronics and Telecommunications of Sfax (ENET’Com)
Telecommunications Engineering · Cybersecurity
August 1, 2023 – June 30, 2025
Preparatory Institute for Engineering Studies of Sfax (IPEIS)
Preparatory Cycle · Physics-Chemistry
August 1, 2021 – June 30, 2022
REF-IT
Full Stack Engineer PHP JavaScript AI
June 7, 2026 – Present
Sfax, Tunisia
Piva Software
AI & Cybersecurity Engineer
February 1, 2025 – June 1, 2025
Tunis, Tunis, Tunisia
Formanet
DevOps Engineering Intern
July 1, 2024 – August 1, 2024
India
Sodalite Agency
Back-End Developer
July 1, 2023 – August 1, 2023
India
MLOps Pipeline for Time-Series Anomaly Detection
January 1, 2025 – January 1, 2025
Designed and implemented a complete MLOps pipeline for time-series anomaly detection, covering the full lifecycle from data ingestion and feature engineering to model deployment and monitoring. The project focused on building a scalable, reproducible, and production-ready ML system. Designed a time-series anomaly detection model using LSTM / GRU / Transformer-based architectures. Engineered features from telemetry streams (latency, throughput, error rates, packet loss, trends). Implemented preprocessing pipelines (scaling, windowing, normalization) to stabilize model behavior. Trained and evaluated models using Python, TensorFlow, Scikit-Learn with statistical baselines. Exposed inference via FastAPI REST endpoints for real-time and batch detection. Containerized training and inference services using Docker for reproducibility. Implemented model versioning and configuration separation to enable controlled updates. Integrated monitoring metrics (prediction drift, anomaly rate) to support retraining decisions. Designed the pipeline with production constraints in mind (latency, reliability, explainability).
Network Intrusion Detection System (Deep Learning / Anomaly Detection)
January 1, 2024 – January 1, 2024
Designed a Python-based intrusion detection system using deep learning for anomaly detection and improved robustness with synthetic data concepts. Built an IDS using TensorFlow for anomaly detection in network traffic. Integrated GAN concepts to generate synthetic samples and improve generalization.
Cultural Fit Analysis
The candidate's diverse project portfolio, spanning full-stack ERP development, AI/ML engineering, and DevOps, indicates adaptability and a broad interest in various technical domains. Their experience aligns well with a dynamic environment that values cross-functional skills. The focus on security-by-design and performance optimization suggests a commitment to best practices, which is a positive cultural indicator. However, the experience level (1 year) is relatively junior for a 'senior' role, which might impact cultural fit in a team expecting immediate senior-level leadership and mentorship.
Soft Skills & Operational Fit
The candidate demonstrates a strong problem-solving aptitude through their project work, particularly in designing end-to-end ML pipelines and optimizing ERP systems. Their experience in troubleshooting production issues and contributing to architectural improvements suggests a proactive and operationally aware mindset. Collaboration is evident through contributions to security tasks and architecture discussions. However, without direct assessment data, specific soft skill nuances like stress handling or team collaboration cannot be fully evaluated.