Staff Quality Assurance Engineer
Pearson · Haifa
Job Title: Staff Quality Assurance Engineer – LAD
Location: Haifa, Israel (Onsite)
About Pearson
Pearson is the world’s leading provider of learning services and materials for higher education institutions and faculties around the globe, operating in over 70 countries.
With a mission to revolutionize the future of learning and courseware , Pearson’s Higher Education team is focused on transforming how students engage with content— developing innovative, consumer-grade digital products that are intuitive, effective, and accessible. We move fast: designing, building, testing, and iterating with agility and purpose.
By putting students at the center of everything we do, we’re creating cross-platform, mobile-first experiences and high-scale web services that are shaping the future of global education.
About the Role:
Pearson is seeking a Staff Quality Assurance Engineer to join our growing, dynamic team. You will help design and develop world-class web applications that are used by millions of learners worldwide.
As a senior team member, you’ll work in a fast-paced, agile environment and take a leading role in quality engineering with strong AI/ML testing experience who can define how Pearson validates intelligent learning systems. The person will own quality strategy for data mapping, APIs, observability, evaluation workflows, and integrations validation.
Key Responsibilities:
Define and drive AI Test Strategy: Create comprehensive test strategies specifically for GenAI products and LLM-based workflows, including model accuracy, bias, safety, and reliability validation.
Develop and maintain AI testing frameworks, including prompt testing and evaluation of model outputs
Build and evolve test automation frameworks, pipelines, and evaluation harnesses for AI/ML models, APIs, and integrated systems.
AI-Specific Quality Validation: Design tests around prompt engineering, hallucination detection, model evaluation metrics, and edge-case scenarios.
System & Integration Testing: Validate end-to-end workflows, including multi-agent orchestration, MCP models, APIs, and UI interactions.
Cross-Functional Collaboration: Partner with Dev, Product, and Data Science to align quality standards with evolving GenAI architectures.