Role summary
The Senior AI Engineer leads the design, build and operation of the machine learning models, large language model (LLM) services and agentic systems that drive Kaplan's AI strategy. Your remit spans learner-facing products and internal AI-first business processes. You will be a technical reference point for the AI Engineering team, owning the design of the systems you build and helping set the standard for how we deliver reliable, secure and scalable AI services.
As the Senior AI Engineer, you will:
- Lead the design, development and delivery of machine learning, LLM and agentic solutions for learner products and internal business workflows.
- Architect agentic workflows, including tool use, structured outputs, multi-agent orchestration and human-in-the-loop patterns.
- Champion engineering standards and best practice, and review the designs and code of other engineers.
- Own the reliability, cost, security and performance of AI services in production.
- Build and maintain evaluation tooling and observability for models and LLM-based systems.
- Mentor AI Engineers and help grow our engineering capability.
- Collaborate with teams across Kaplan, including product, data science, design and learning teams, to translate requirements into technical direction.
- Stay current with new AI tools and techniques and set direction on their practical adoption.
Detailed responsibilities
Technical leadership and mentoring
- Set and champion standards for engineering quality, code review and reusable patterns.
- Lead the technical approach on ambiguous or novel problems.
- Own the design of the systems you build and shape architectural decisions across the AI platform, aligned with enterprise architecture.
- Mentor and develop AI Engineers through review, pairing and technical guidance.
Model and agent development
- Lead algorithm and framework selection, and design retrieval and grounding strategies, prompts and embeddings.
- Design, build and evaluate agentic workflows using frameworks such as Microsoft Agent Framework.
- Evaluate models and LLM-based systems using agreed metrics and methods, including golden datasets, LLM-as-judge evaluation, and tracing and observability tooling.
- Partner with data science colleagues, who own modelling and evaluation methodology, while you own production systems and evaluation tooling.
Data management
- Work with data teams to source, clean and version training and retrieval data.
- Ensure data handling meets GDPR and Kaplan's privacy policies.
Deployment and MLOps
- Own containerised deployment (Docker/Kubernetes) to cloud platforms.
- Lead automated testing, CI/CD, infrastructure-as-code, monitoring and alerting.
- Manage the capacity, cost and performance of AI services in production.
Collaboration and support
- Provide technical guidance to product, learning and content teams.
- Lead the resolution of production issues and their root causes.
- Act as a technical consultant to business stakeholders on AI-first workflow redesign.
Innovation and growth
- Assess emerging techniques and paradigms and set direction on their practical adoption.
- Champion new ideas by building prototypes and translating research into tangible solutions.
- Share findings with product and learning stakeholders with clear impact statements.
You'll also carry out other duties, within the broad scope and spirit of your role, as requested by your manager. Our business continuously evolves, so your role will too.
What you might be doing now
Your current role, or recent roles, may be:
- AI Engineer at Kaplan, ready to step up
- Senior Machine Learning Engineer
- Senior Software Engineer leading AI features
- Machine Learning Engineer leading the delivery of LLM or agentic systems
What you'll bring to the role
This role suits an experienced, pragmatic engineer who leads by example: someone who balances rapid experimentation with production-level rigour and raises the standard of those around them.
You will have:
- 5+ years experience in software or machine learning engineering.
- Substantial experience (typically 2+ years) building and operating LLM-based or agentic systems in production.
- Strong Python skills and knowledge of ML libraries (PyTorch, TensorFlow, scikit-learn).
- Experience with agent and LLM frameworks (e.g. Microsoft Agent Framework, LangGraph) and prompt engineering.
- Strong MLOps experience: CI/CD, container orchestration and infrastructure-as-code, with cloud platforms (Azure preferred).
- Knowledge of NoSQL/document databases (e.g. Azure Cosmos DB) and vector search (e.g. Azure AI Search), plus a solid grounding in relational/SQL database design and querying.
- Experience leading technical decisions, mentoring engineers and reviewing designs and code.
- A strong understanding of data privacy, security and responsible AI, and the ability to explain complex ideas to non-specialists.
Desirable
- Experience with Google's agent platform (Gemini Enterprise Agent Platform/Vertex AI, including the Agent Development Kit).
- Familiarity with agent interoperability standards such as the Model Context Protocol (MCP) and Agent2Agent (A2A).
- Additional programming languages such as C# and the .NET framework.
- Experience with education-specific standards such as xAPI, LTI or LMS plug-ins.
