About the role
Descripción del puesto / Funciones
* Design and execute end-to-end testing strategies specifically tailored for Machine Learning models, Generative AI systems, RAG architectures, and Autonomous Agents.
* Validate model accuracy, fairness, bias detection, explainability, robustness, and performance across diverse and edge-case datasets.
* Execute adversarial testing, prompt-injection, jailbreaking, and red-teaming to evaluate prompt robustness and behavioral variations under stress.
* Validate agentic workflows, including multi-step reasoning paths, state transitions, tool execution, and fallback behaviors during service failures.
* Evaluate LLM outputs for correctness, grounding, factuality, consistency, safety, and hallucination reduction.
* Assess vector store behavior, document chunking logic, retriever configurations, and semantic search accuracy.
* Conduct API, performance, latency, throughput, and concurrency testing on AI inference endpoints and data pipelines.
* Ensure compliance with AI ethics, data privacy laws, business rules, and insurance regulatory guidelines, maintaining audit-ready test evidence and behavioral reports.
* Define AI quality KPIs, establish test governance, and build automated testing frameworks integrated into CI/CD pipelines.
* Collaborate closely with Data Scientists, ML Engineers, SMEs, and DevOps teams while mentoring junior QA engineers and creating reusable test accelerators.
Requisitos mínimos
* Experience & Specialization: Proven senior/lead expertise in software quality engineering with a dedicated focus on AI/ML systems and GenAI applications.
* Programming & Automation: Advanced proficiency in Python for test automation, data validation, and custom AI testing scripts.
* GenAI & RAG Ecosystems: Hands-on experience with GenAI frameworks, vector databases, chunking strategies, and retrieval evaluation.
* Model Evaluation & Metrics: Deep understanding of data validation, model evaluation metrics, fairness/bias testing, and drift detection (data and concept drift).
* API Testing: Expertise in testing AI services and model endpoints using tools such as Postman, REST Assured, or Python REST clients.
* DevOps, Cloud & Infrastructure: * Experience with CI/CD pipelines for continuous testing integration. * Exposure to cloud platforms hosting AI deployments. * Working knowledge of containerization and orchestration environments (e.g., Docker, Kubernetes). * Familiarity with Big Data ecosystems for large-scale AI testing.
* Security & Governance: Experience in AI ethics, compliance testing, observability tools, and security testing for data pipelines and model-serving endpoints.
Requisitos valorables
* Advanced Red Teaming: Hands-on experience building automated adversarial test suites and automated synthetic data generation for rare edge cases.
* Framework Automation: Direct implementation of specialized LLM evaluation frameworks (e.g., Ragas, DeepEval, TruLens).
* Observability Setup: Advanced configuration of AI monitoring dashboards and automated regression testing workflows for retrained models.
Idiomas
English is a must
Ubicación
Barcelona