AI Engineer (LLM)

TL;DR

AI Engineer (LLM): Building and shipping AI-powered features end-to-end with an accent on RAG pipelines, LLM integration, and backend service development. Focus on designing intelligent systems like copilots and chatbots, optimizing performance, and ensuring scalability in production environments.

Location: Must be based in Poland

Company

A global innovation-driven company with 3000+ professionals, focused on building advanced Generative AI and LLM-based solutions for industries including healthcare, finance, and legal.

What you will do

• Build and ship AI-powered features such as chatbots, copilots, and automation tools.
• Design and implement RAG pipelines using embeddings and vector search.
• Integrate LLM APIs like OpenAI and Anthropic into production systems.
• Develop backend services using Python or Node.js to support AI workflows.
• Improve system reliability through rigorous evaluation, testing, and iteration.
• Debug and resolve issues related to hallucinations, latency, and cost inefficiencies.

Requirements

• Must be based in Poland
• 2+ years of experience in Machine Learning or AI-related roles.
• Strong coding skills in Python or JavaScript.
• Hands-on experience working with LLM APIs and building RAG pipelines.
• Proven ability to build and ship production-ready systems.
• Solid understanding of ML fundamentals.

Nice to have

• Experience with LLM evaluation, fine-tuning, or model optimization.
• Exposure to agent frameworks or multi-step reasoning systems.
• Domain experience in finance, healthcare, or legal sectors.

Culture & Benefits

• Highly innovation-driven and collaborative international environment.
• Opportunity to work closely with founders and product teams.
• Focus on solving complex real-world AI challenges.