Quick, practical role. Test AI models, find faults and propose fixes. Real tests, fast reports, clear actions. Direct, no fluff.
What you’ll do: Test models and AI-based systems to find errors, biases, security issues and usability problems. Create reproducible test cases and work with the technical team to prioritise fixes. Assess output quality for coherence, factuality and safety.
Responsibilities
- Design and run test cases for AI functionalities.
- Detect and document bugs, unexpected behaviours and biases.
- Reproduce failures and provide clear, verifiable steps.
- Evaluate outputs for coherence, factuality and safety.
- Propose improvements for prompts, pipelines and validation criteria.
- Keep records and produce clear, actionable reports.
Requirements
- Practical experience testing software or AI models (hands-on, not just theory).
- Ability to describe faults clearly and make them reproducible.
- Basic ML/AI knowledge and familiarity with common failure modes (hallucinations, bias, drift).
- Communication skills to work with technical teams.
- Analytical mindset and results orientation.
Desirable
- Experience with automated testing frameworks.
- Knowledge of fairness and security evaluation in AI.
- Familiarity with issue-tracking and incident-management tools.
- Experience testing conversational interfaces or NLP systems.
Conditions and contact
- Conditions: to be determined (contract, hours and salary to be agreed).
- Contact: to be defined.
- Be ready to send a short CV and examples or logs of tests you have performed.
📌 experto con ia (Gijón)
🏢 HR Enterprise Yearly
📍 Gijón
Postulate a este anuncio
Muestra tus habilidades a la empresa, rellenar el formulario y deja un toque personal en la carta, ayudará el reclutador en la elección del candidato.