AI / LLM Engineer – RAG & Agentic AI

Job Summary

We are looking for an experienced AI / LLM Engineer to design and develop enterprise AI applications involving Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents and intelligent workflow automation.

The successful candidate will have strong Python and AI application development experience and be comfortable independently delivering AI solutions from solution design and development through testing, deployment and continuous improvement.

The role will support initiatives including enterprise RAG platforms, corporate knowledge systems, AI assistants, proactive AI agents, document intelligence and workflow automation.

Key Responsibilities

• Design and develop LLM applications, RAG systems, AI assistants and agentic AI solutions.
• Build AI agents capable of retrieving information, using tools/APIs, executing workflows and interacting with users.
• Develop document ingestion, chunking, embedding, retrieval, prompting, memory and agent-orchestration capabilities.
• Integrate AI applications with enterprise systems, databases, APIs, document repositories and third-party services.
• Implement and optimise semantic search, vector retrieval, reranking and retrieval strategies.
• Work with LLM APIs, open-source models, vector databases and appropriate AI/agent frameworks.
• Develop evaluation approaches for retrieval quality, response accuracy, faithfulness, hallucination, latency and task completion.
• Implement secure enterprise AI patterns including access controls, permission-aware retrieval, guardrails, monitoring and failure handling.
• Independently deliver AI projects across requirements, architecture, development, testing, deployment and optimisation.
• Deploy and maintain AI applications using modern software-engineering and DevOps practices.
• Collaborate with product, software, cloud, data, security, IT and business teams.
• Monitor production performance and continuously improve AI application quality and usability.

Requirements

• Bachelor's degree or above in Computer Science, AI, Machine Learning, NLP, Data Science, Engineering or related discipline.
• At least 2 years of relevant experience in LLM applications, RAG, information retrieval, NLP, AI agents or AI application development.
• Strong hands-on Python programming experience.
• Hands-on experience with LLMs, embeddings, vector databases, semantic search or retrieval systems.
• Practical experience designing or developing RAG architectures.
• Good understanding of prompt engineering, retrieval strategies, evaluation and hallucination mitigation.
• Experience developing AI agents, tool/function calling, agent workflows or backend/API integrations.
• Experience integrating applications with APIs, databases or enterprise systems.
• Ability to independently deliver end-to-end AI/LLM projects.
• Familiarity with Git, automated testing, CI/CD and containerised deployment.
• Strong communication and stakeholder-management skills.

Registration No.: R25156061

EA No.: 11C3373