Senior AI Quality Engineer

This is a fully remote position, open to applicants in Egypt.

📋 Description

• Review product updates prior to their launch.

• Supervise the quality assurance process throughout the product development lifecycle.

• Establish functional and performance testing protocols.

• Create testing frameworks and automate processes across backend, frontend, and mobile platforms.

• Develop coverage for API, contract, service-level, integration, web E2E, component, visual, RTL, mobile, performance, and load testing.

• Manage shared fixtures, environments, test data, parallelization, and CI pipelines.

• Generate and maintain tests based on specifications, code, and production traffic.

• Classify failures as bugs, flakes, environment issues, or test degradation.

• Create self-healing locators and suite-health tools.

• Construct AI-feature evaluation infrastructure with datasets, scoring, and regression detection.

• Assess behavior in Arabic and English, including RTL interfaces and region-specific POS, tax, and payment regulations.

• Develop agentic AI workflows that analyze differences, execute suites, reproduce failures, suggest fixes, and submit pull requests.

• Implement end-to-end exploratory testing, coverage-gap identification, release-risk assessments, and human-escalation workflows.

• Coordinate planning, tool utilization, retries, state management, memory, sandboxed execution, and multi-agent transitions.

• Integrate with CI, Jira, observability, and MCP-style tool interfaces.

• Utilize context engineering, reliability practices, and LLM operations such as tracing, prompt/version management, latency and cost budgeting, model routing, and fine-tuning or distillation decisions.

⛳️ Requirements

• Recent hands-on experience with LLM-backed systems relied upon by real users.

• Proficient in Python.

• Familiarity with at least one of .NET, Java, or TypeScript.

• Experience delivering tested, maintained production software instead of notebooks.

• Automation experience across multiple platforms.

• Experience managing release-gating test suites for backend and web or mobile user interfaces.

• Ability to build evaluation systems and quantify improvements with metrics.

• Practical understanding of prompting, structured output, tool utilization, retrieval, and agentic AI orchestration.

• Awareness of trade-offs in contemporary LLM systems.

• Strong foundational knowledge in testing, including test design, automation frameworks, and CI/CD practices.

• Emphasis on adoption and evaluating engineering work based on usage.

• Familiarity with Playwright, Appium, or Maestro.

• Knowledge of API, contract, service-level, integration, web E2E, component, visual, RTL, mobile, performance, and load testing.

• Understanding of agentic AI orchestration, multi-step planning, memory and state management, sandboxed execution, multi-agent patterns, MCP-style tool integration, context engineering, evaluation, reliability, and LLM operations.

🏝️ Benefits

• Highly competitive compensation packages, including bonuses and potential equity options.

• Regular training opportunities.

• Annual learning stipend.

• Chance to collaborate with a diverse team of over 30 nationalities across 14 countries.

• Autonomy in your work.

• Mentorship opportunities.

• Ambitious goals and avenues for career advancement.