AI Engineer (Python / LLM)

AI Engineer (Python / LLM)

Itexus is looking for an experienced Senior AI Engineer to join our engineering team and help shape a next-generation AI platform for the aviation industry.

You’ll become part of an international team building an AI layer that integrates across multiple enterprise aviation products, helping engineers and end users work with complex technical documentation, maintenance data, and intelligent workflows.

The role combines AI engineering and backend development in roughly equal proportions. You’ll work with LLM-powered services, multi-agent systems, RAG architectures, backend APIs, and enterprise integrations while collaborating closely with an international engineering team.

Success in this role requires curiosity, ownership, and the ability to work with evolving requirements. Engineers are expected to understand product workflows, propose technical solutions, evaluate trade-offs, and independently deliver production-ready functionality.

Location: Poland preferred, open to candidates across Europe.

What you will do

• Develop backend services and APIs using Python and FastAPI
• Design, develop, and maintain production-ready AI services powered by Large Language Models (LLMs)
• Build and enhance multi-agent systems using LangChain and similar frameworks
• Design and optimize RAG (Retrieval-Augmented Generation) pipelines
• Build and improve tools used by AI agents (Harness Engineering)
• Work with embeddings, vector search, and vector databases
• Integrate AI capabilities into existing enterprise applications
• Optimize prompts, LLM interactions, and token usage
• Integrate and maintain internal and external APIs
• Test, validate, and continuously improve AI-powered functionality
• Participate in architecture discussions, technology selection, and technical decision-making
• Understand business workflows and collaborate with stakeholders to design practical AI solutions

What we are looking for

• 5+ years of commercial software engineering experience
• Strong Python programming skills
• Commercial experience developing backend applications with FastAPI or similar frameworks
• Experience working with Large Language Models (LLMs) in production environments
• Hands-on experience building AI applications using LangChain or similar agent frameworks
• Hands-on experience designing and implementing RAG solutions
• Ability to evaluate technologies, make technical decisions, and justify architectural choices
• Good understanding of embeddings, vector search, and vector databases
• Experience with PostgreSQL, SQLAlchemy, and Alembic
• Experience integrating REST APIs and third-party services
• Strong analytical and problem-solving skills
• Comfortable working independently with a high level of ownership and responsibility
• English level B2+ or higher

Nice to Have

• Experience with LangGraph or other agent orchestration frameworks
• Experience with prompt engineering and LLM optimization
• Experience building AI applications in production environments
• Experience working with multiple vector databases (PGVector, Qdrant, Pinecone, Weaviate, Milvus, etc.)
• Experience with Docker and CI/CD pipelines
• Experience with Azure, AWS, or GCP
• Experience with ETL pipelines, streaming technologies, or data integration tools
• Experience working in startup or rapidly evolving product environments
• Experience in aviation, enterprise software, or other complex business domains

Why Join Us

• Work on a strategic AI initiative that spans an entire aviation product ecosystem
• Build production AI solutions used by enterprise customers
• Influence technical decisions and product evolution
• Work in an environment with a high level of ownership, technical autonomy, and real impact on engineering decisions
• Collaborate with experienced international engineers using modern AI technologies, including LLMs, RAG, agent-based architectures, and backend services