AI Engineer - LLM/RAG Systems Development

We are seeking a hands-on AI Engineer to join our AI engineering team focused on building production-grade LLM and RAG systems for large-scale document processing. This is an applied AI engineering position, not a research role, where you will build real features used in daily operations.

In this role, you will build and improve LLM/RAG pipelines for processing extensive document sets and develop Python microservices that power GenAI features. You will work extensively with embeddings, vector databases, and retrieval logic while building data ingestion and document processing workflows. The position involves deploying and operating solutions in an AWS environment and collaborating with a small team of AI engineers and developers.

We are looking for candidates with strong Python engineering fundamentals and hands-on experience with LLMs, embeddings, RAG, and prompt engineering. Experience deploying AI solutions, preferably in AWS, is essential. Additional experience with web crawling and Java/backend knowledge would be advantageous.

This is a 3-month contract position with high likelihood of extension, potentially contributing for approximately one year total. You will make key contributions to a rapidly scaling GenAI platform with the freedom to experiment and move fast using modern AI tooling. The role offers a hybrid working arrangement combining remote work with office presence.

This opportunity is perfect for an AI engineer who wants to work on cutting-edge technology in a fast-paced environment, building solutions that have immediate real-world impact. Join our team and help shape the future of AI-powered document processing systems.