We are looking for a Quality Engineer Lead Expert to lead quality assurance of our AI systems: ML models, LLM-based applications, RAG pipelines and autonomous agents. The role covers functional, non-functional, security and compliance testing in an insurance context. It works closely with AI engineers, data scientists, DevOps teams and SMEs.

Goals and deliverables

Main Responsibilities
- Design and execute test strategies for ML models, LLMs and agents (accuracy, fairness, bias, explainability, robustness)
- Validate LLM and RAG outputs: grounding, hallucination, retrieval accuracy, vector stores, chunking logic
- Run adversarial, prompt-injection and red team testing
- Benchmark latency, throughput, concurrency and multi-agent performance; validate fallback and retry logic




- Build automated test frameworks for AI/ML pipelines, including synthetic data and regression testing of retrained models
- Define model quality KPIs, produce audit-ready evidence and mentor junior testers

Experience Required
- Software testing focused on AI systems (ML models, LLMs, agents)
- Python for test automation, data validation and AI testing scripts
- API, performance and security testing of AI services and model endpoints
- AI ethics, data privacy and regulatory compliance testing
- Testing AI on cloud platforms and Big Data ecosystems at scale

📌 Quality Engineer AI based (Barcelona)
🏢 Ubique Systems
📍 Barcelona