Senior AI Agent Test Automation Engineer

Own quality for Nexxa AI agents through Python automation and exploratory testing across industrial systems and operational scenarios.

As a Senior or Staff SDET, you will build production-grade evaluation harnesses, simulators, regression suites, and CI/CD quality gates. You will test LLM-based agents across planning, tool selection, execution, recovery, and final outputs. The work combines API, contract, integration, end-to-end, performance, and reliability testing with manual trace review, red-teaming, and release verification.

Key Responsibilities:

• Build evaluation harnesses and regression suites for LLM-based agents
• Integrate automated evaluations into CI/CD quality gates
• Develop simulators, mocks, and sandbox environments for industrial tools
• Review traces, outputs, and agent behavior manually
• Turn failures and attacks into reproducible automated tests

Requirements:

• Five-plus years in SDET, QA, or software engineering
• Strong Python programming and software engineering practices
• Manual and automated testing experience for distributed systems
• Experience with CI/CD, Docker, and Kubernetes
• Experience testing APIs, microservices, and LLM-based products

Apply your automation, evaluation, and exploratory testing expertise to Nexxa’s high-stakes industrial AI systems.