19 hours ago
Remote, Poland +5 moreSenior
Responsibilities
- Design, build, and run AI agents covering requirement analysis, test case design, test generation, execution, and failure triage.
- Build multi-agent pipelines that convert Jira tickets into reviewed test cases and automated tests integrated into CI.
- Use MCP servers such as Playwright MCP for agent-driven browser interaction, exploratory testing, and self-healing locators.
- Maintain agent prompts, tools, context, and skills as versioned code, with human review checkpoints and trust controls.
- Extend Selenium and Playwright automation frameworks and support migration from Selenium to Playwright.
- Write and maintain reviewable test code in Java, Python, and TypeScript and integrate tests into CI/CD with parallel execution and reporting.
- Create evaluation sets and metrics for agent accuracy, false positives, flake rate, and time saved per release.
- Test MCP servers and AI agent tools for response accuracy, authentication, permissions, error handling, and real-agent behavior.
- Investigate failures to distinguish product defects, test instability, environment problems, and agent mistakes.
- Apply security-minded practices to agent tooling, including secrets handling, data access limits, and prompt-injection risk reduction.
- Partner with QA managers, developers, and product managers, mentor QA engineers, and communicate trade-offs and results to leadership.
Requirements
- 8+ years of software quality assurance experience, including at least 5 years in test automation.
- At least 1 year of hands-on experience bringing agentic AI into a real QA team workflow.
- Experience building an agent or multi-agent workflow that generates, runs, or triages tests in a production QA process and measuring its output.
- Hands-on experience with MCP servers and AI coding agents such as Claude Code, Cursor, or GitHub Copilot.
- Strong programming skills in Java, Python, and TypeScript.
- Deep experience building and maintaining Playwright and Selenium WebDriver automation frameworks and using the Page Object Model.
- Strong manual, exploratory, API, and SQL-based data validation testing skills.
- Experience running automation in CI/CD pipelines and working with Git.
- Strong judgment about human validation of AI output, debugging, and driving complex or intermittent failures to root cause.
- Preferred experience with custom MCP servers, agent tools, Claude Agent SDK, LangGraph, OpenAI Agents SDK, or similar frameworks.
- Preferred experience designing LLM evaluations with golden datasets, scoring rubrics, and prompt regression checks.
- Preferred experience with Selenium-to-Playwright migrations, cybersecurity or security-focused products, security testing, and LLM-specific risks.
- Preferred experience testing data-heavy platforms, ETL pipelines, or integrations with Jira, ServiceNow, Tenable, or Qualys.
- Preferred experience presenting technical topics, mentoring QA engineers, and working in Agile/Scrum environments.
Benefits
- Remote workplace in Georgia.
- Opportunity to work on agentic AI, advanced QA automation, and cybersecurity-focused software products.
- Collaboration with QA managers, developers, product managers, and engineering leadership.
About Intetics
Intetics provides custom software development, quality assurance, and distributed engineering teams for enterprises and tech-driven companies. Its services span application and mobile development, systems integration, data processing, and GIS solutions, delivered via project work or dedicated offshore teams. Founded in 1995 and headquartered in Naples, Florida, the privately held firm holds ISO 9001 and ISO 27001 certifications.