LLM/AI Engineer

Responsibilities:

• Design, develop, and maintain LLM-powered solutions, including Retrieval-Augmented Generation (RAG) pipelines, entity extraction modules, and structured content generation frameworks

• Implement and optimize LLM workflows using Azure OpenAI Service

• Build scalable solutions for integrating vector databases, embeddings generation, document chunking, and metadata enrichment

• Collaborate with data engineers on data pipelines and prompt chains in production environments

• Define and implement prompt engineering strategies and fine-tuning approaches for LLM-based solutions

• Ensure compliance with enterprise data governance, security, and regulatory standards, particularly in highly regulated industries (e.g., pharmaceuticals)

Required Skills & Qualifications:

• Proven hands-on experience building LLM-based applications, including RAG pipelines and knowledge retrieval systems

• Strong proficiency with Azure OpenAI (deployment, prompt design, rate limiting, model configuration)

• Solid understanding of NLP techniques, including entity extraction, summarization, and classification

• Experience designing document ingestion and embedding pipelines using tools such as LangChain or custom implementations

• Familiarity with vector databases such as FAISS, Weaviate, or Pinecone

• Practical knowledge of prompt engineering, few-shot learning techniques, and evaluation of generative outputs

• Ability to write production-grade Python code and work in cloud-native environments (e.g., Databricks, Azure Functions)

Nice to have:

• Experience with Databricks Model Serving, MLflow, and serving fine-tuned or custom LLMs via REST APIs

We offer:

• B2B contract (up to 250 PLN/h net + VAT)

• 100% remote work

• Wide range of projects (internal and international)

• Dedicated certification budget

• Annual evaluation meetings to define an individual development path

• Benefits package

• Integration trips