Job Description: Your objective will be to ensure the validation of the performance, efficiency, and robustness of AI models by developing test strategies adapted to AI use cases (RAG, autonomous agents, LLM), with particular attention to responsible and ethical aspects. Your responsibilities will include: Collaborating with the product and data teams to ensure the alignment of test results with business needs; developing the test approach, scenarios, and validation plans covering functional and non-functional aspects (performance, security), as well as vulnerabilities; implementing testing processes and tools adapted to AI use cases (RAG validation, autonomous agents); monitoring and sharing key performance indicators (KPIs) to measure model effectiveness; and industrializing AI testing practices within the teams. To monitor technological developments in AI testing frameworks and methodologies. To be proactive in transforming concepts into operational testing solutions.

Desired Candidate Profile

Qualifications

Diploma m (e) of a Bac+5 in computer science.

Experience: Minimum 3 years.

Required skills:

• Methodologies: Agile Testing, ISTQB guide, Data/AI acculturation (GenAI and non-GenAI)
• Programming: Python, Pandas, NumPy
• Generative AI: RAG, Prompt Engineering, Agentique, LLM
• AI frameworks: LangChain, LangGraph or equivalents
• AI testing tools: Giskard, RAGAS, Deep-Eval or similar solutions for model evaluation