AI QA - Lead Engineer / Manager

About Our Team

Quality is what makes AI trustworthy. Lenovo is hiring an AI QA - Lead Engineer/ Manager that ensures our AI systems are not just powerful but reliable, fair, and safe for deployment at scale. You'll shape the quality culture that allows the Core Intelligence team to innovate rapidly while maintaining production excellence. You will lead the AI Quality Engineering function in the AI Ecosystem team, building the testing infrastructure and quality gates that ensure our AI/ML models, agentic systems, and data pipelines meet the highest standards of accuracy, fairness, and reliability before reaching millions of users.

What You'll Do

• Design and implement comprehensive test frameworks for AI/ML systems: LLMs, vision models, RAG pipelines, agentic workflows.
• Build automated evaluation systems for model outputs-accuracy, relevance, bias detection, hallucination monitoring.
• Create quality benchmarks and continuous testing pipelines for generative AI (content quality, safety, brand alignment).
• Develop performance monitoring infrastructure: model drift detection, data quality validation, inference latency tracking.
• Establish AI-specific quality gates and work with product/engineering teams in Agile sprints to define acceptance criteria.
• Lead a team of AI QA engineers and drive best practices for responsible AI development.
• Stay ahead of AI testing trends: adversarial testing, red-teaming, AI safety evaluation.

Basic Qualifications

• 7+ years in QA/test engineering, with 3+ years focused on AI/ML systems.
• Bachelor's degree in Engineering or Computer Science.
• Experience with ML model evaluation: classification metrics, NLP evaluation (BLEU, ROUGE, human eval), vision model testing.
• Experience building test automation frameworks (Python, pytest, CI/CD pipelines).

• Strong collaboration skills-comfortable working with data scientists, ML engineers, and product managers.
• Passion for AI quality and keeping current with testing methodologies for generative AI.
• Knowledge of AI risks: bias, fairness, safety, hallucinations, adversarial attacks.