وظائف Internship في تونس

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> <p><span>About us:</span></p><br> <p><span>At Cognira, we strongly believe that people are the biggest asset of our company. Our hand-picked team consists of passionate, collaborative, and forward-thinking individuals from all over the globe. We are passionate about making science easy and accessible to retailers, helping them get more value from people, data, and systems. We bring together expertise in retail, science, and scalable technologies to automate and enhance the quality of decision-making through software and consulting services.</span></p><br> <p><span>We are proud to have a growing team of domain experts and data scientists, as well as a culture that fosters strong and long-lasting relationships with our clients.&nbsp;</span></p><br> <p><span>Our Locations:&nbsp;</span></p><br> <ul> <li><span>Atlanta, GA, US&nbsp;</span></li> <li><span>Tunis, Tunisia</span></li> <li><span>Istanbul, Turkey</span></li> <li><span>Paris, France</span></li> <li><span>Porto, Portugal</span></li> </ul> <p><span>Our values:</span></p><br> <ul> <li><span>Be nice and trustworthy</span></li> <li><span>Put our customers first</span></li> <li><span>Succeed together</span></li> <li><span>Never stop improving</span></li> </ul> <p><span>Are you ready to grow with us?</span><span>To find out more about Cognira, please visit our website at</span><span>www.cognira.com</span></p><br> <p><span>Please submit your resume in English.&nbsp;</span><br></p><br> <p><span>I- Frontend Team Internship Topics:&nbsp;</span><br></p><br> <p><span>Topic1 : A Visual Screen Builder with AI-Ready Design Handoff</span><br></p><br> <p><span>Project Overview:&nbsp;</span></p><br> <p><span>Cognira's design system is documented in Storybook, but Product Managers and UX designers currently require engineering support to assemble screens using available components. Additionally, design handoff between design and engineering teams remains a manual and error-prone process.</span></p><br> <p><span>This project will create a visual screen builder that allows non-technical users to construct screens from existing Storybook components, generate structured specifications, and expose those specifications to AI coding agents through an MCP server.</span><br></p><br> <p><span>Deliverables</span><br></p><br> <p><span>Screen Builder Application</span></p><br> <ul> <li><span>Component catalog automatically generated from Storybook metadata.</span></li> <li><span>Visual canvas for building screens using predefined layouts.</span></li> <li><span>Auto-generated property editor based on TypeScript component definitions.</span></li> <li><span>Save and load functionality for screen configurations.</span></li> </ul> <p><span>Screen Specification Framework</span></p><br> <ul> <li><span>JSON Schema automatically generated from component prop definitions.</span></li> <li><span>Validation of screen specifications against generated schemas.</span></li> <li><span>Human-readable and AI-readable Markdown exports.</span></li> </ul> <p><span>MCP Integration</span></p><br> <ul> <li><span>An MCP server that exposes screen specifications to AI coding agents.</span></li> <li><span>Support for AI-powered validation and implementation using approved components and properties.</span></li> </ul> <p><span>Required Skills</span></p><br> <ul> <li><span>TypeScript and React</span></li> <li><span>Front-end application development</span></li> <li><span>JSON and schema design</span></li> <li><span>Understanding of component-based design systems</span></li> <li><span>Problem-solving and software architecture skills</span></li> </ul> <p><span>Preferred Skills</span></p><br> <ul> <li><span>Storybook</span></li> <li><span>MCP (Model Context Protocol)</span></li> <li><span>TypeScript metadata and code generation</span></li> <li><span>Design systems and UX workflows</span></li> <li><span>AI-assisted development tools</span></li> <li><span>API and server development</span></li> </ul> <p><span>Topic2: Interactive MCP Apps for PromoAI's Agent Cora</span></p><br> <p><span>Project Overview</span></p><br> <p><span>PromoAI is a SaaS platform that helps retailers plan, forecast, and analyze promotional performance. Its AI assistant, Cora, answers business users' questions in natural language, helping them understand forecasts, identify promotion conflicts, and gain insights into their promotional activities.</span></p><br> <p><span>Cora can already be accessed through AI applications such as Claude using the Model Context Protocol (MCP), but responses are currently delivered as plain text. MCP Apps, a recent extension to the protocol, allow tools to return interactive web applications directly within AI chat experiences.</span></p><br> <p><span>In this project, you will enhance Cora's user experience by building interactive MCP Apps that allow users to explore charts, sort and export tables, select products and stores, and interact with forecast data directly from their AI assistant. You'll work across both a TypeScript backend and a modern web frontend while validating the experience across multiple AI platforms.</span></p><br> <p><span>Deliverables</span></p><br> <ul> <li><span>Implement MCP Apps support within Cora's MCP server, providing interactive experiences alongside text-based responses for clients that do not support MCP Apps.</span></li> <li><span>Develop a library of reusable interactive views, including:</span> <ul> <li><span>Answer cards with charts and data tables</span></li> <li><span>Promotion and event information cards</span></li> <li><span>Forecast breakdown visualizations</span></li> <li><span>Promotions calendar views</span></li> </ul> </li> <li><span>Build interactive components that communicate directly with backend services, including:</span> <ul> <li><span>Product and store pickers</span></li> <li><span>Alerts inbox</span></li> <li><span>Exportable data tables</span></li> </ul> </li> <li><span>Implement adaptive styling that follows the theme of each host AI application in both light and dark modes.</span></li> <li><span>Create automated tests covering both frontend components and backend server changes.</span></li> <li><span>Produce a compatibility report for Claude, ChatGPT, Gemini, and VS Code.</span></li> <li><span>Stretch Goal: Develop a shared component library that can be used across both Cora's internal chat interface and external AI applications.</span></li> </ul> <p><span>Required Skills</span></p><br> <p><span>Web Development</span></p><br> <ul> <li><span>TypeScript / JavaScript</span></li> <li><span>React</span></li> <li><span>Vite</span></li> <li><span>Nginx</span></li> </ul> <p><span>Fundamental Knowledge</span></p><br> <ul> <li><span>LLM tool calling</span></li> <li><span>AI agents</span></li> <li><span>Model Context Protocol (MCP)</span></li> <li><span>Automated testing</span></li> </ul> <p><span>Preferred Skills</span></p><br> <ul> <li><span>Python development</span></li> <li><span>Web security fundamentals, including iframes, Content Security Policy (CSP), and OAuth</span></li> <li><span>Building interactive charts and data tables for web applications</span></li> <li><span>UI component design and frontend performance optimization</span></li> </ul> <p><span>II- Backend Team Internship Topics:&nbsp;</span></p><br> <p><span>Topic 1: Test-Impact Selection Service</span></p><br> <p><span>Project Overview</span></p><br> <p><span>Currently, every code change triggers the entire test suite, even when only a small portion of the codebase is affected. This project aims to build an intelligent test-selection service that analyzes code changes, determines impacted areas, and executes only the relevant tests while providing clear explanations for each selection.</span></p><br> <p><span>Deliverables</span></p><br> <ul> <li><span>Build a service that identifies and executes tests affected by a code change.</span></li> <li><span>Provide explanations showing why each test was selected.</span></li> <li><span>Generate replay reports using historical commits to demonstrate reduced testing time without missed failures.</span></li> <li><span>Integrate the solution into the CI/CD pipeline.</span></li> <li><span>Deliver technical documentation and a final project demonstration.</span></li> </ul> <p><span>Required Skills</span></p><br> <ul> <li><span>Scala</span></li> <li><span>Software testing fundamentals</span></li> <li><span>Object-oriented programming</span></li> <li><span>Git</span></li> </ul> <p><span>Preferred Skills</span></p><br> <ul> <li><span>PostgreSQL</span></li> <li><span>SemanticDB</span></li> <li><span>CI/CD pipelines</span></li> <li><span>Static code analysis</span></li> <li><span>Software architecture and dependency analysis</span><br></li> </ul> <p><span>Topic 2: Human-in-the-Loop AI Development Assistant</span></p><br> <p><span>Project Overview</span></p><br> <p><span>As AI-generated code becomes increasingly common, developers need tools that provide visibility, review capabilities, and human oversight throughout the development process.</span></p><br> <p><span>This project focuses on building a full-stack application that enables developers to review AI-generated code changes, request explanations, collaborate on reviews, and maintain control over AI-assisted development workflows.</span></p><br> <p><span>Deliverables</span></p><br> <ul> <li><span>Build a web application for reviewing AI-generated code changes.</span></li> <li><span>Enable developers to comment on specific code blocks.</span></li> <li><span>Allow users to request explanations and clarifications for generated code.</span></li> <li><span>Provide pull-request walkthrough capabilities.</span></li> <li><span>Create a collaborative review experience that combines AI assistance with human validation.</span></li> <li><span>Deliver documentation and a final demonstration.</span></li> </ul> <p><span>Required Skills</span></p><br> <ul> <li><span>Full-stack web development</span></li> <li><span>React</span></li> <li><span>SQL databases</span></li> <li><span>Software engineering fundamentals</span></li> <li><span>Git and collaborative development workflows</span></li> </ul> <p><span>Preferred Skills</span></p><br> <ul> <li><span>Go or Python</span></li> <li><span>PostgreSQL</span></li> <li><span>AI-assisted development tools</span></li> <li><span>Large Language Models (LLMs)</span></li> <li><span>Code review and developer productivity tools</span></li> </ul> </div>

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> <span>Please submit your CV in English and indicate your level of English proficiency.<br> Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems.<br> Participation is project-based, not permanent employment.<br> About the Role You’ll design coding tasks that challenge frontier AI coding agents.<br> Each task is a self-contained Docker environment with a broken piece of software; an AI agent attempts the fix; automated tests verify the outcome.<br> Your deliverable is the full task package: broken code, tests, instructions, and a reference solution proving the task is solvable.<br> Responsibilities : Invent a realistic developer scenario — a real bug, a broken ETL, a missing feature — not a toy problem.<br> Build a reproducible Docker environment with pinned dependencies.<br> Write a pytest that verifies outcomes, not specific commands — deterministic, non-flaky, and does not leak the fix.<br> Write an instruction.<br>md that reads like a Jira ticket a developer would receive.<br> Write a reference solve.<br>sh proving the task is solvable.<br> Calibrate difficulty so current state-of-the-art agents solve the task 20–60% of the time.<br> Iterate based on feedback from expert QA reviewers.<br> Later: review other authors’ tasks as a QA reviewer.<br> Not in scope Data labeling, prompt engineering.<br> Production code to ship — you design problems and verification for AI agents.<br> Leetcode puzzles — scenarios must look like real developer work.<br> Not every candidate task ships — quality over quantity.<br> Requirements 3+ years of production software development in one backend stack — Python, Go, Node.<br>js, Java, or Rust.<br> Depth in one stack beats breadth.<br> Python + pytest fluency — required regardless of primary stack.<br> The task harness is pytest-based even when the broken app is in another language.<br> Fixtures, parametrize, monkeypatch, timeouts, conftest.<br>py. Docker authoring — reproducible Dockerfiles, pinned dependencies, multi-stage builds when needed, non-root user.<br> Linux &amp; Bash — comfort debugging inside containers (strace, lsof, journalctl); shell beyond set -euo pipefail.<br> AI coding agent experience — Claude Code, Cursor, Roo Code, or similar, on non-trivial work.<br> You can cite a specific time the AI was confidently wrong and how you caught it.<br> English — B2+ written.<br> Not a fit Data Science, ML, or Computer Vision engineers without backend-engineering output.<br> Manual QA testers without automation or test authoring.<br> Frontend-only, low-code / no-code, IT Support, or Business Analysts.<br> Engineers who have never written pytest from scratch.<br> Junior, intern, or assistant as the most recent role.<br> Preferred qualifications Domain depth in Security, System Administration (nginx / systemd / cron), Scientific Computing (NumPy / PyTorch / SciPy), DevOps, or Git internals.<br> Modern Python tooling (uv, poetry, pyproject.<br>toml). Coverage tooling (pytest-cov, coverage.<br>py, gcov, llvm-cov, kcov).<br> Fuzzing or property-based testing (Hypothesis).<br> Prior contribution to agent-evaluation benchmarks or related frameworks.<br> Process Apply → Pass qualification (90-minute sample-task screen + short behavioral interview) → Join a project → Complete tasks → Get paid.<br> Time commitment Onboarding: ~10 hours per first task.<br> Steady state: ~5 hours per task, 2–4 parallel tasks per author.<br> Realistic weekly load: 8–20 hours.<br> Higher volume available for top performers.<br> You choose when and how to contribute; tasks must be submitted by the deadline and meet acceptance criteria.<br> Compensation: Paid contributions, rates up to $35/hour *.<br> Task-based compensation equivalent to hourly rate, depending on performance and volume.<br> Some projects include incentive payments.<br> *Rates vary based on expertise, skills assessment, location, project needs, and other factors.<br> Higher rates may be provided to highly specialized experts.<br> Lower rates may apply during onboarding or non-core project phases.<br> Payment details are shared per project.<br> Apply Submit your CV via the Mindrift platform.<br> Indicate your English level, note this role (Software Engineering Evaluation Specialist — Terminal Bench), and include a GitHub profile link if available.<br></span> </div>