Senior AI Engineer

Job Purpose

The Senior AI Engineer is responsible for designing, building, and evolving the intelligence layer of Croner’s generative AI solutions. This includes implementing Retrieval-Augmented Generation (RAG) pipelines, agentic workflows, model adaptation techniques, and evaluation strategies that deliver accurate, trustworthy, and domain-specific AI behaviour.

As part of the Croner’s AI team, the role translates approved architecture, strategy, and product direction into high-quality, production-ready AI implementations, contributing hands-on expertise across retrieval, reasoning, model behaviour, and evaluation. The Senior AI Engineer works in close collaboration with the AI Platform Engineer—who owns infrastructure, runtime, and operational concerns—to ensure AI capabilities are scalable, maintainable, and well-integrated the wider platform.

The role also provides hands-on technical support to junior AI engineers and plays a key role in shaping the quality and robustness of Croner’s AI capabilities through deep implementation experience.

Objectives

• Deliver high-quality generative AI capabilities focused on correctness, faithfulness, and robustness.

• Implement and continuously improve RAG and agentic systems that effectively leverage Croner’s proprietary content.

• Establish strong experimentation and evaluation practices to measure and improve AI performance.

• Apply appropriate model adaptation techniques (prompting, fine-tuning, distillation) to optimise quality and cost.

• Provide technical support and mentoring to junior AI engineers.

• Contribute to technical design discussions to ensure AI solutions are pragmatic, scalable, and aligned with platform capabilities.

Key Responsibilities

1. RAG & Generative AI Engineering

• Design and implement generative AI workflows using LlamaIndex, AWS Strands Agents SDK and more.

• Build and evolve RAG pipelines, including retrieval logic, prompt orchestration, grounding strategies, and response structuring.

• Implement agentic or workflow-based patterns where appropriate, focusing on determinism, explainability, and maintainability.

2. Retrieval & Knowledge Engineering

• Implement and refine retrieval strategies such as chunking approaches, reranking logic, and retrieval fusion.

• Contribute to advanced retrieval techniques, including Graph-RAG and structured knowledge representations, where they add value.

• Work closely with the AI Platform Engineer to ensure retrieval logic aligns with vector search, indexing, and ingestion pipelines.

3. Model Adaptation & Optimisation

• Implement fine-tuning, instruction tuning, and knowledge distillation techniques to adapt models to domain-specific requirements.

• Evaluate trade-offs between prompt-based approaches and model adaptation in terms of quality, latency, and cost.

• Support experimentation with different models and configurations to improve AI outcomes.

4. Evaluation, Experimentation & Quality

• Design and implement evaluation workflows for generative AI systems.

• Define and run experiments to assess retrieval quality, answer correctness, faithfulness, and robustness.

• Ensure experiments are reproducible, well-documented, and suitable for integration into wider evaluation and monitoring frameworks.

5. Technical Leadership & Team Development

• Provide hands-on technical support to junior AI engineers.

• Conduct code reviews, design walkthroughs, and technical mentoring.

• Establish and promote best practices for AI development, experimentation, and documentation.

6. Collaboration

• Work closely with the Director of Search & Generative AI on the evolution of AI capabilities and technical direction.

• Partner with the AI Platform Engineer to transition AI logic from experimentation into production.

• Collaborate with product and delivery roles to clarify requirements and support delivery.

Skills & Requirements

Technical Skills

• Strong proficiency in Python for production-grade AI development.

• Hands-on experience with LlamaIndex, Strands Agent SDK and LangChain / LangGraph.

• Solid experience implementing Retrieval-Augmented Generation (RAG) systems; Graph-RAG experience is a plus.

• Practical experience with fine-tuning, instruction tuning, or knowledge distillation.

• Strong understanding of evaluation and experimentation methodologies for generative AI systems. Experience with MLFlow.

• Familiarity with AWS, Bedrock, AgentCore and Databricks environments is advantageous.

• Fluency with code versioning and CI/CD pipelines.

Experience

• Demonstrable experience delivering complex software, data science, or machine learning solutions in professional environments, showing sustained depth of expertise and progression in responsibility.

• Demonstrable experience building, deploying, and operating production-grade ML or AI systems, including customer-facing or business-critical applications.

• Demonstrable experience acting as a technical lead or system owner for complex platforms, with responsibility for technical design decisions, implementation quality, and delivery outcomes.

• Demonstrable experience working with large or complex datasets and production-grade data pipelines, including considerations of performance, scalability, and reliability.

Behavioural Skills

• Experience operating as a senior AI engineer or technical lead within an engineering team.

• Strong problem-solving skills and attention to implementation quality.

• Ability to balance experimentation with delivery.

• Clear and effective communicator within technical and cross-functional teams.