AI Engineer – Large Language Models & Document Intelligence

About the role

We are seeking an experienced AI Engineer to join our Baku office and work on cutting‑edge AI projects that support legal and business document workflows. You will design, deploy, and maintain private AI infrastructure, focusing on large language models and document intelligence solutions.

Key responsibilities

• Deploy and optimise open‑source Large Language Models (LLMs) on on‑premise hardware.
• Design and implement Retrieval‑Augmented Generation (RAG) architectures and vector‑database pipelines.
• Build AI‑powered processing pipelines for PDFs and other document formats, including OCR and information extraction.
• Configure GPU‑based inference environments and manage local AI infrastructure.
• Develop AI‑driven document classification, extraction, and automated analysis tools for legal and business documents.
• Create AI 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, understanding, and OCR pipelines.
• Demonstrated prompt‑engineering skills and experience with AI agents.
• Experience deploying and managing on‑premise AI environments, including GPU inference and performance optimisation.

Required skills

• Python
• Large Language Model frameworks (e.g., Hugging Face Transformers)
• Retrieval‑Augmented Generation, embeddings, vector databases
• Document classification and OCR technologies
• Prompt engineering and AI agents
• GPU inference, model deployment, performance optimisation
• vLLM, Ollama, LangChain, LlamaIndex (or similar)
• NVIDIA GPUs, CUDA ecosystem
• Docker, Linux, Microsoft Azure environments