Senior AI Engineer

We are looking for a AI Engineer to join our Team, to bring to life new features and support the move of our services and products to modern architecture. You will be working closely with Product Owner, Product Designer, Domain Architect and your team members clarifying business needs and technical requirements and defining how to support them in the best way.

In close collaboration with other teams, your team will introduce new features and improvements for catalog pages in the website to provide better experience for more than 11 millions of our customers!

We are looking for a Senior AI Engineer to design, build, and operate production-grade AI applications. In this role, you will develop backend services and APIs that integrate large language models into business workflows, with a strong focus on reliability, safety, observability, and maintainability.

This is an engineering-first role for someone with strong software engineering fundamentals and hands-on experience delivering LLM-powered systems to production. You should be comfortable owning services end to end, adapting them as models and requirements evolve, and helping teams adopt effective AI engineering practices.

• Strong Python and backend engineering skills for building 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 discipline, observability, evaluation, and failure handling
• Solid practical understanding of AI safety, reliability, and evaluation, including guardrails, fallback patterns, and output validation
• A pragmatic approach to solving messy real-world problems with clean, maintainable systems
• Curious, delivery-focused, and comfortable working in a fast-moving technical landscape

• Experience designing and operating LLM systems with orchestration frameworks such as Lang Chain, MCP, RAG, Graph databases
• Familiarity with platform engineering practices such as Infrastructure as Code and performance testing for production APIs
• Experience working with Java or Kotlin
• Ability to prototype and experiment quickly using tools such as streamlit and Jupyter notebooks
  
  Background in applied NLP tasks such as classification or PII detection

• 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 approaches
• 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
• Work closely with engineers, product owners, and domain stakeholders to turn ambiguous use cases into production-ready solutions
• Continuously improve systems through model upgrades, prompt iteration, and operational optimisation

Here are several aspects of our team and work environment that contributes to a positive and fulfilling experience:

We work in self-organized teams following Scrum methodology, respecting and valuing everyone´s opinion.

We learn from each other and share knowledge, through pair programming, code reviews, and many training opportunities.

We deliver value by developing new features, maintaining existing products and improving all the infrastructure we need for it, so we also would like to have a colleague that likes to be cross-functional.

We are committed to delivering high-quality products, and believe that continuous delivery, clean code, and a Dev Ops mindset are key to achieving this goal.

Our team values a friendly and collaborative environment, and we greatly encourage open communication and teamwork. We believe in a team approach and do not assign blame, instead working together to build and maintain the system.

We embrace diversity, having colleagues from over 50 countries. This means our working language is English.