AI Engineer - LLMs, Document Intelligence and Private AI Infrastructure

About the role

An experienced AI Engineer is sought to work on real-world AI projects involving large language models, document intelligence and private AI infrastructure.

Key responsibilities

• Deploy and optimise open-source large language models (LLMs)
• Design, implement and maintain private (on-premise) AI systems
• Develop Retrieval-Augmented Generation (RAG) architectures
• Build AI-powered pipelines for processing PDFs and other document formats
• Configure GPU-based inference environments and local AI infrastructure
• Develop AI-driven document classification and information extraction solutions
• Automate the analysis of legal and business documents with AI
• Build AI systems that generate response letters from historical data and similar cases

Required profile

• Hands-on experience with AI and LLM technologies
• Experience deploying and managing on-premise AI environments
• Experience with GPU inference, model deployment and performance optimisation

Required skills

• Strong Python proficiency
• RAG, embeddings and vector databases
• Document classification and understanding, OCR and document processing pipelines
• Prompt engineering and AI agents
• Preferred: vLLM, Ollama, Hugging Face Transformers, LangChain, LlamaIndex, NVIDIA CUDA, Docker, Linux, Microsoft Azure; preferred also: LegalTech or document automation experience