Senior AI Engineer (LLM)

TL;DR

Senior AI Engineer (LLM/Python): Design, build, and operate production-grade AI services and backend applications integrating large language models into business workflows with an accent on reliability, safety, observability, and maintainability. Focus on LLM-powered workflows, prompt design, context management, structured outputs, tool calling, and implementing guardrails and evaluation approaches.

Location: Hybrid in Krakow, Poland (60% office, 40% remote)

Company

Trailblazers in pet e-commerce with over 25 years experience, serving 12 million customers across Europe.

What you will do

• Build and operate production-grade AI services and backend applications in Python
• Design and implement LLM-powered workflows including prompt design, context management, structured outputs, and tool calling
• Define robust contracts for APIs and AI outputs
• Test, evaluate, and improve AI services through automated testing, prompt iteration, and measurable evaluation
• Implement safety and reliability controls such as validation, guardrails, fallbacks, and error handling
• Monitor and improve production systems using logs, metrics, traces, and AI observability tooling
• Collaborate with engineers, product owners, and stakeholders to deliver production-ready solutions
• Continuously improve systems through model upgrades, prompt iteration, and operational optimisation

Requirements

• Location: Hybrid in Krakow, Poland
• Strong Python and backend engineering skills for production-grade services and APIs
• Proven experience developing and shipping LLM-powered applications in production
• Strong understanding of prompt engineering, structured outputs, context management, and tool calling
• Experience integrating foundation models and LLM platforms such as Azure OpenAI, OpenAI, or Bedrock
• Strong experience in API design, testing, deployment, observability, evaluation, and failure handling
• Solid practical understanding of AI safety, reliability, and evaluation including guardrails and output validation

Nice to have

• Experience with LLM orchestration frameworks such as LangChain, RAG, graph databases
• Familiarity with platform engineering practices like Infrastructure as Code and performance testing
• Experience with Java or Kotlin
• Ability to prototype quickly using Streamlit and Jupyter notebooks
• Background in applied NLP tasks such as classification or PII detection

Culture & Benefits

• Hybrid working: 60% office in Krakow, 40% remote, option for 20 days abroad in approved countries
• Private medical care, life insurance, Multicafeteria system including Multisport card
• Two extra vacation days plus days off on 24th and 31st December
• Development opportunities, excellent training, wellbeing offers, subsidised transport or bike leasing
• 20% discount on all products
• Multinational team across Munich, Madrid, Krakow, Wroclaw, London, Vienna