AI Test Engineer; m​/f​/d

AI Test Engineer

We are looking for an AI Test Engineer to assure the quality, safety, and reliability of AI-enabled software used in connected product experiences. You will work at the intersection of AI application quality, automated testing, APIs, cloud and edge services, and connected devices. This is a hands-on role for a specialist who can turn ambiguous product behavior into precise, repeatable evaluation scenarios and clear engineering feedback.

You are an active and thoughtful user of modern generative AI tools. You understand their capabilities and limitations and use tools such as ChatGPT, OpenAI Codex, Git Hub Copilot, or comparable solutions to accelerate test design, automation, debugging, analysis, and documentation - while critically validating their output.

You will collaborate with software, machine learning, UX, hardware and product teams to validate AI-driven user journeys from prompt or voice input through orchestration, tools, services, and device responses. Your work will make prototypes and product demonstrations reproducible, observable, and ready for release decisions.

What You Will Do

• Lead end-to-end quality engineering for AI-enabled applications, including conversational and agentic workflows, model integrations, orchestration layers, APIs, user interfaces, and connected-device experiences.
• Design and execute structured evaluations for LLM and agent-based behavior: functional correctness, instruction following, tool use, grounding, safety boundaries, consistency, failure handling, and regression risk.
• Prototype, build and maintain automated test solutions, including reusable test data, evaluation datasets, test harnesses, API collections and release-validation pipelines.
• Translate product requirements and real user journeys into deterministic and exploratory test scenarios, acceptance criteria and measurable quality signals.
• Validate multi-turn and multimodal interaction flows, including speech or text input, device controls, audio or media-related features and context-aware personalization when applicable.
• Test REST APIs and distributed services, including request/response contracts, schemas, authentication, error handling, backward compatibility, telemetry and observability.
• Investigate defects using logs, traces, test results and system behavior; isolate root causes, create high-quality defect reports and verify fixes.
• Review code changes and collaborate with developers on testability, unit-test coverage, CI quality gates and practical release criteria.
• Prepare and validate integrated software-and-device environments across Linux, Windows, mobile platforms, cloud services, local services and networked hardware.
• Communicate quality risk, test evidence, known limitations and release readiness clearly to technical and non-technical stakeholders.
• Apply AI-assisted engineering tools in your daily work to generate and refine test scenarios, accelerate automation, analyze failures, explore edge cases and improve technical documentation. Critically review and validate all AI-generated output.

What You Need to Be Successful

• Bachelor's or Master's degree in Computer Science, Software Engineering, Electrical Engineering or a related technical field.
• 5+ years of hands-on experience in software quality engineering, test automation, systems integration or software validation.
• Demonstrable experience testing AI-enabled software products, such as LLM applications, conversational systems, agentic workflows, recommendation systems or ML-powered features. General manual-software-testing experience alone is not sufficient.
• Strong understanding of how to evaluate non-deterministic AI behavior and convert it into repeatable, evidence-based quality checks.
• Hands-on experience with Python and automated testing frameworks; confidence reading and contributing to production-adjacent test code.
• Practical experience with REST APIs, JSON, schema/contract validation and test automation for distributed services.
• Experience with Git-based development, pull-request review, issue tracking, CI/CD and technical documentation.
• Strong troubleshooting skills across application, service, network and device layers; comfortable working with logs, traces, and telemetry.
• Experience using AI-assisted engineering tools responsibly to improve test design, automation, debugging and documentation.
• Ability to communicate defects and quality trade-offs precisely, work independently and operate effectively when requirements evolve.

Bonus Points if You Have

• Experience with LLM evaluation frameworks, prompt testing, retrieval-augmented generation, tool/function calling, agents, or model-provider integration.
• Experience validating AI features in embedded, automotive, consumer-electronics, audio, mobile or other connected-device environments.
• Experience with speech interfaces, text-to-speech, speech recognition, audio or media controls, personalization, or multimodal user experiences.
• Experience with cloud platforms and local/edge deployment, containers,…