Sr./Lead QA Automation Engineer – AI Agent

Sr./Lead QA Automation Engineer – AI Agent Are you a quality engineer who wants to build confidence in a fast-evolving AI agent — not just execute manual test cases? At SimCorp, we are developing an internal AI agent that supports the software development lifecycle (SDLC): a production-grade, distributed agent hosted in Azure — running 24/7, accessible to everyone in the company, and spanning deep integrations with our engineering systems, secure code execution, and remote development capabilities on user machines.  WHAT MAKES US, US  Join some of the most innovative thinkers in FinTech as we lead the evolution of financial technology. If you are an innovative, curious, collaborative person who embraces challenges and wants to grow, learn and pursue outcomes with our prestigious financial clients, say Hello to SimCorp!  At its foundation, SimCorp is guided by our values — Caring, Customer success-driven, Collaborative, Curious, and Courageous. Our people-centered organization focuses on skills development, relationship building, and client success. We take pride in cultivating an environment where all team members can grow, feel heard, valued, and empowered.  If you like what we’re saying, keep reading!   WHY THIS ROLE IS IMPORTANT TO US We are looking for a QA Automation Engineer to own and evolve the quality strategy for this product. The product's risk sits in cross-service behavior — where agent runs, tool calls, external integrations, and cloud infrastructure meet. The role blends hands-on manual and exploratory testing of new features and AI behavior with designing and building the automated test system — acceptance, integration, contract, and post-deployment validation — that lets the team ship quickly without breaking critical engineering workflows.   WHAT YOU WILL BE RESPONSIBLE FOR As a QA Automation Engineer on this team, you will:  Test strategy and hands-on testing  Define and own the product's test strategy across unit, functional, integration, acceptance, post-deployment, and exploratory testing.  Perform hands-on manual and exploratory testing of new features, AI-agent behavior, and edge cases before and alongside automation.  Design approaches for testing non-deterministic AI/LLM behavior, tool-use correctness, and prompt regressions.  Automated coverage  Build browser-level acceptance tests that cover key user journeys end to end, from the UI down to persistence and background processing.  Create validation for MCP endpoints, including authentication flows, client compatibility, and tool schemas.  Design contract and replay-based tests for critical external integrations where live systems are slow, expensive, or unstable.  Strengthen test coverage for the highest-risk execution surfaces: sandboxed code execution and the agent's remote sessions on user machines.  Release confidence and test infrastructure  Add post-deployment smoke tests that catch environment, configuration, and identity failures,…