AI/Agentic Engineer

We’re hiring an experienced and ambitious  AI/Agentic Engineer to join our growing team at Itexus!

About Project:
The project is a global software and information services company focused on enhancing aviation safety and efficiency. Their solutions help reduce costs, improve aircraft reliability, and streamline technical knowledge sharing across the industry.

Key Responsibilities:

• Design and development of an AI-augmented framework for autonomous UI testing;
• Automation of the full test lifecycle: generation, refactoring, and adaptation of tests in response to changes in the UI and product code using LLMs (Copilot, etc.);
• Development, optimization, and management of a library of prompts, instructions, and context for the effective operation of AI assistants;
• Design and maintenance of MCP (Model Context Protocol) servers to extend Copilot’s capabilities with custom project data;
• End-to-end integration of the testing system with team collaboration tools: TestRail, Jira, and CI/CD (GitLab CI/CD);
• Creation of tools and practices to democratize the test writing process, enabling less experienced engineers to leverage the AI system’s capabilities.

Requirements:

• Excellent knowledge of JavaScript/TypeScript/Python;
• Deep practical experience in UI test automation using Playwright (experience with Cypress/Selenium will be considered, but Playwright is a priority);
• Practical experience with AI-assisted dev tools (GitHub Copilot, Cursor, etc.) and proven ability to write effective prompts for code generation;
• Experience integrating automated tests into CI/CD processes;
• Experience working with TestRail and Jira;
• Systemic and architectural thinking. Ability to design complex systems, not just write scripts;
• Ability to work with ambiguous, evolving requirements and R&D tasks;
• Proactivity, ownership, and results-oriented approach;
• Ability to explain complex concepts and inspire the team to adopt new approaches.

Will be a plus:

• Practical experience in building RAG systems and working with agentic frameworks (e.g., LangChain);
• Experience working with LLM APIs (OpenAI, HuggingFace, Anthropic) and understanding their capabilities and limitations;
• Experience in advanced prompt engineering or model fine-tuning;
• Background in backend development (creating APIs, microservices) for AI features;
• Experience deploying and hosting ML models in the cloud (AWS);
• Familiarity with ML lifecycle tools: Docker, Git, MLflow;
• Understanding of the full AI/ML pipeline.

 

We’ll be happy to tell you more about the company when you meet with us!