AI Engineer

Job Description

DataMinds Analytics is seeking an AI Engineer for our Chicago innovation hub to build production applications powered by large language models. You will design RAG systems, fine-tune open models, build evaluation harnesses, and ship AI features — from intelligent document processing to conversational assistants — used by enterprise clients. Our Chicago hub builds AI products for Fortune 500 clients, from contract intelligence to autonomous research assistants handling thousands of documents daily.

This is a senior role at the frontier of applied AI. You will influence our AI platform strategy, publish technical blog posts, and work with the latest models and tooling. We offer top-quartile compensation and a team of exceptional engineers to learn from. You will also shape our evaluation methodology for LLM systems, contribute to our AI safety guidelines, and receive dedicated GPU resources for personal experimentation.

Responsibilities

Design and build LLM-powered applications (RAG, agents, copilots)
Fine-tune and evaluate open-source language models
Build evaluation frameworks and guardrails for AI systems
Develop vector search and knowledge-retrieval pipelines
Optimise inference latency and cost for production workloads
Stay current with AI research and prototype new capabilities

Requirements

4-7 years of software/ML engineering with recent LLM focus
Strong Python skills and LLM framework experience (LangChain, LlamaIndex)
Hands-on RAG system design and vector database knowledge
Experience fine-tuning models and running evaluations
Understanding of prompt engineering and agent architectures
Familiarity with model serving (vLLM, Triton) preferred

Skills

Python, LangChain, LlamaIndex, PyTorch, Vector Databases, RAG, Prompt Engineering, AWS, Docker, Evaluation Frameworks

Benefits

Top-quartile salary with significant bonus
Equity participation programme
Comprehensive health, dental and vision insurance
Hybrid working in downtown Chicago
AI conference and research budget