LLM Engineer

About the role

The LLM Engineer will join an existing development team to enhance and expand a complex, dynamic application. You will work closely with global product owners and engineering stakeholders, delivering high‑quality AI‑driven features from concept to production.

Key responsibilities

• Design, implement, and maintain RESTful APIs using Python frameworks such as FastAPI or Flask.
• Develop and deploy micro‑services in containerised environments (Docker, Kubernetes).
• Integrate large language model APIs (OpenAI, Anthropic) and LLM frameworks (LangChain, LlamaIndex) into production systems.
• Build Retrieval‑Augmented Generation (RAG) pipelines, including vector databases and semantic search.
• Write and optimise prompts for diverse use‑cases and ensure generative solutions scale beyond proof‑of‑concept.
• Collaborate with cross‑functional teams across time zones to solve complex problems and own feature delivery end‑to‑end.
• Apply security best practices, including authentication and data protection, to backend services.

Required profile

• Self‑motivated professional who can plan and execute technical work independently.
• Effective communicator comfortable collaborating with product owners and global teams.
• Data‑driven problem solver with a systems‑level mindset, blending data‑science and engineering principles.
• Continuously updates technical knowledge and embraces new AI technologies.
• Demonstrates ownership, delivering high‑quality solutions with minimal supervision.

Required skills

• Python
• FastAPI / Flask
• REST APIs
• Microservices architecture
• Docker
• Kubernetes
• Artificial intelligence, machine learning, natural language processing
• OpenAI API, Anthropic API
• LangChain, LlamaIndex
• Model Context Protocol (MCP)
• Multi‑agent systems
• Retrieval‑Augmented Generation (RAG), vector databases, semantic search
• Prompt engineering
• Server‑sent events, event‑driven architecture, messaging systems
• Backend security best practices, authentication, data protection