AI Engineer

Role overview

Responsibilities

• check_circle Design and build AI-enabled features for various education products, from assessments to tutoring.
• check_circle Work with education partners and internal stakeholders to understand assessment practices, quality expectations and real-world constraints.
• check_circle Build evaluation approaches that measure output quality, consistency, usefulness and failure modes.
• check_circle Develop retrieval, prompt-management, orchestration and structured-output workflows where appropriate.
• check_circle Integrate LLM APIs, AI services and education data into reliable product capabilities.
• check_circle Design practical human-review, control and escalation workflows for AI-supported decisions.
• check_circle Improve the reliability, latency, cost and quality of AI services in production.
• check_circle Build prototypes quickly, test them against real education use cases and productionise successful approaches.
• check_circle Develop suitable guardrails, monitoring and auditability for AI outputs.
• check_circle Work with Backend Engineers on service architecture, data handling, integrations and scalability.
• check_circle Work with Product Engineers to ensure AI features are understandable, useful and trustworthy for teachers and students.
• check_circle Use AI-assisted development tools appropriately while maintaining strong engineering judgement, testing, privacy and security standards.
• check_circle Write clean, tested and maintainable code.

Basic qualifications

• 2+ years of professional data science, applied AI or machine-learning engineering experience.
• Experience building AI-enabled features, prototypes or production applications using LLM APIs or related AI services.
• Strong programming ability in Python, TypeScript/Node.js or similar languages.
• Experience with prompt design, structured outputs, retrieval workflows, AI orchestration or agentic workflows.
• Experience evaluating AI quality, reliability and safety beyond informal manual testing.
• Solid understanding of APIs, databases, cloud services and production software architecture.
• Ability to balance experimentation with disciplined engineering, testing, privacy and security standards.
• A self-directed approach to investigating new methods, testing assumptions and improving product quality.
• Comfortable working with non-technical stakeholders and education partners to understand the real problem behind a feature request.
• Strong ownership, debugging and problem-solving skills.
• Clear written and spoken English.

Preferred qualifications

• Experience with retrieval-augmented generation, embeddings, vector databases or document-processing pipelines.
• Experience designing evaluation datasets, test harnesses, quality metrics or human-review workflows.
• Experience with data pipelines, ETL and production level data science.
• Experience with privacy, security, auditability or responsible-AI practices.
• Experience with modern cloud platforms and containerised application deployment.
• A degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science or a related technical discipline.