08/20/2026 updated
100 % available
AI/ML Engineer & Full-Stack Developer specializing in Agentic Systems and Evaluation
sfax, Tunisia
Only remote
Master 1, Information Systems and Network DevelopmentAI AgentsMachine LearningMulti-Agent SystemsGenerative AIFull Stack DevelopmentFront End Software DevelopmentArtificial Intelligence Markup Language (AIML)
AI Evaluation Engineering
Expertise in building evaluation harnesses for AI agents, including rule-based code graders, LLM-as-a-judge metrics using DeepEval and GEval, golden and regression test fixtures, and CI-integrated evaluation suites with pytest and GitHub Actions.
AI & Agentic Systems
Hands-on experience designing and orchestrating multi-agent systems using CrewAI, applying prompt engineering fundamentals, and integrating LLM APIs such as OpenAI to automate complex workflows.
Full-Stack Software Development
Proficiency in building scalable full-stack web applications using React.js, Spring Boot, Node.js, and Next.js, integrated via RESTful APIs with secure authentication, dynamic role management, and performance optimizations.
Machine Learning
Knowledge of machine learning fundamentals including Perceptron and gradient descent implemented from scratch, as well as data analysis and visualization using NumPy, Pandas, Matplotlib, and Seaborn.
Programming Languages
Proficiency in multiple programming languages including JavaScript, Python, Java, C++, C, C#, PHP, and Dart.
Frameworks & Libraries
Experience with a wide range of frameworks including React.js, Django, Node.js, Next.js, Spring Boot, ASP.NET Core, Angular.js, and .NET.
Frontend Development
Skills in frontend technologies including HTML, CSS, Tailwind CSS, and DaisyUI for building responsive and modern user interfaces.
Databases
Experience working with relational and non-relational databases including MySQL, MongoDB, PL/SQL, and PostgreSQL.
DevOps
Familiarity with DevOps tools and practices including Git, Docker, CI/CD fundamentals, Postman, and Linux system administration.
Mobile Development
Experience in mobile application development using Android and Flutter frameworks.
Data Analysis & Visualization
Ability to analyze and visualize data using Power BI, NumPy, Pandas, Matplotlib, and Seaborn.
Expertise in building evaluation harnesses for AI agents, including rule-based code graders, LLM-as-a-judge metrics using DeepEval and GEval, golden and regression test fixtures, and CI-integrated evaluation suites with pytest and GitHub Actions.
AI & Agentic Systems
Hands-on experience designing and orchestrating multi-agent systems using CrewAI, applying prompt engineering fundamentals, and integrating LLM APIs such as OpenAI to automate complex workflows.
Full-Stack Software Development
Proficiency in building scalable full-stack web applications using React.js, Spring Boot, Node.js, and Next.js, integrated via RESTful APIs with secure authentication, dynamic role management, and performance optimizations.
Machine Learning
Knowledge of machine learning fundamentals including Perceptron and gradient descent implemented from scratch, as well as data analysis and visualization using NumPy, Pandas, Matplotlib, and Seaborn.
Programming Languages
Proficiency in multiple programming languages including JavaScript, Python, Java, C++, C, C#, PHP, and Dart.
Frameworks & Libraries
Experience with a wide range of frameworks including React.js, Django, Node.js, Next.js, Spring Boot, ASP.NET Core, Angular.js, and .NET.
Frontend Development
Skills in frontend technologies including HTML, CSS, Tailwind CSS, and DaisyUI for building responsive and modern user interfaces.
Databases
Experience working with relational and non-relational databases including MySQL, MongoDB, PL/SQL, and PostgreSQL.
DevOps
Familiarity with DevOps tools and practices including Git, Docker, CI/CD fundamentals, Postman, and Linux system administration.
Mobile Development
Experience in mobile application development using Android and Flutter frameworks.
Data Analysis & Visualization
Ability to analyze and visualize data using Power BI, NumPy, Pandas, Matplotlib, and Seaborn.
Languages
EnglishFluentFrenchFluentSpanishBasic knowledge
Project history
Built an evaluation harness for the AI Agent Crew project with deterministic code-based graders running in CI via pytest and GitHub Actions, combined with DeepEval GEval LLM-as-a-judge metrics for qualitative checks. Includes golden and regression fixtures to prove each grader catches known failure modes.
Designed a 4-agent system with CrewAI that automates product research and procurement reporting: a query-generation agent, a web-search agent (Tavily), a scraping agent using Pydantic schemas, and a report-writing agent orchestrated sequentially with a shared knowledge source and JSON-structured outputs.
Implemented the Perceptron algorithm from scratch for binary classification on the 150-sample Iris dataset using Python, NumPy, Pandas, and Matplotlib, covering gradient descent and decision-boundary visualization.