Be the one building AI-powered experiences where they matter most.
At Genesys, we help organizations create better customer experiences through AI-powered experience orchestration. Our platform connects people, systems, data and AI to help organizations deliver more personalized service, improve operational efficiency and build stronger customer relationships.
Help build, support and operate technology used by more than 8,000 organizations in over 100 countries – moving AI from possibility to production in real-world enterprise environments every day.
Genesys Cloud Copilot is our agentic AI platform. We build the framework that lets AI agents reason, use tools, and work alongside contact center professionals at enterprise scale. We’re looking for a Senior Test Engineer to help define how agentic AI systems get tested and trusted.
This isn’t a conventional QA role. You’ll work with AI agents, Model Context Protocol (MCP) servers, and LLM-driven workflows, where outputs aren’t always deterministic and the old testing playbooks often don’t apply. You’ll design test strategies and build Python testing frameworks. If you want to work at the leading edge of AI quality engineering in a fast-moving team where your ideas ship, this role is for you.
Key Responsibilities
The primary responsibilities for this role include (but are not limited to):
* Design and run test strategies for agentic AI systems. This covers agents, tool and MCP integrations, and multi-step workflows, so that Copilot behaves reliably, safely, and predictably for our customers.
* Build and maintain scalable Python test frameworks and automation. These should let the team validate changes quickly and confidently, with fast feedback in CI/CD.
* Develop approaches for testing non-deterministic behavior. This includes evaluation datasets, scoring methods, and quality metrics that measure agent quality in a meaningful, repeatable way.
* Contribute to Test Architecture initiatives across teams. Define standards, patterns, and tooling that raise the quality bar beyond Copilot.
* Drive adoption of AI SDLC practices. Pilot AI-assisted testing and development workflows, share what you learn, and help other teams adopt them effectively.
* Own testing projects end to end. Scope the work, plan it, and deliver it independently, adjusting priorities as requirements change.
* Work with a wide range of stakeholders. This includes developers, product managers, architects, and leadership. You’ll communicate quality risks, test results, and recommendations clearly so they can make informed release decisions.
* Thrive in an agile, fast-changing environment. Adapt test plans and frameworks as the product and the AI landscape change.
Minimum Requirements
* 5+ years of professional software testing / quality engineering experience, with a proven track record of delivery
* Strong Python skills, with hands-on experience building test frameworks and automation (e.g., pytest)
* Proven ability to design test strategies, test plans, and test cases for complex, distributed, or cloud-based systems
* Experience testing APIs, services, and integrations in CI/CD pipelines
* Familiarity with LLMs, AI agents, or MCP, and a strong interest in going deeper
* Ability to work independently and manage projects end to end with minimal oversight
* Excellent communication skills, with the ability to explain technical quality topics to both technical and non-technical stakeholders
* Comfort working in agile teams, with frequent change and shifting priorities
* Strong analytical and problem-solving skills, with a curious, investigative mindset
Desirable Skills
* Experience testing non-deterministic systems (e.g., LLM-based applications, ML models, probabilistic outputs)
* Experience with AI agent evaluation, such as eval frameworks, LLM-as-judge, benchmark design, or tools like DeepEval, Ragas, or LangSmith
* Experience with performance, load, or scalability testing (e.g., Locust, k6, JMeter)
* Experience…