AI Engineer – LLMs, Document Intelligence & Private AI

About the role

We are seeking an experienced AI Engineer to design, deploy, and maintain cutting‑edge AI solutions. The role focuses on large language models, document intelligence, and private on‑premise AI infrastructure for real‑world business applications.

Key responsibilities

• Deploy and optimise open‑source Large Language Models (LLMs) for production use.
• Design, implement and maintain private, on‑premise AI systems.
• Develop Retrieval‑Augmented Generation (RAG) architectures and vector‑database pipelines.
• Build AI‑powered workflows for processing PDFs, OCR, and other document formats.
• Configure GPU‑based inference environments and manage local AI infrastructure.
• Create AI‑driven document classification and information‑extraction solutions.
• Automate analysis of legal and business documents using AI.
• Develop systems that generate response letters based on historical case data.

Required profile

• Hands‑on experience with AI and LLM technologies.
• Strong proficiency in Python programming.
• Practical experience with RAG, embeddings and vector databases.
• Background in document classification, OCR and document understanding.
• Experience deploying and managing on‑premise AI environments, including GPU inference and performance optimisation.

Required skills

• Python
• Large Language Models (LLMs)
• RAG, embeddings, vector databases
• Document classification & OCR pipelines
• Prompt engineering & AI agents
• GPU inference, NVIDIA CUDA
• Docker, Linux
• Microsoft Azure
• Frameworks such as vLLM, Ollama, Hugging Face Transformers, LangChain, LlamaIndex