(Senior) AI Engineer – AI Booster Team (f|m|d)

At idealo, Generative AI (GenAI) is becoming a multiplier across every team. The AI Booster Team is our internal technical competence center: we pair with product teams, build reusable GenAI building blocks and share best practices company-wide. As an AI Engineer, you will design, prototype and productionise LLM-powered solutions that shorten the path from idea to first release while coaching fellow engineers on their GenAI journey.

This position is available full-time or part-time.

About your new role

• Pair with cross-functional teams to ship GenAI features – from discovery workshop to live deployment in weeks, not months.

• Design and implement LLM workflows: prompt templates, RAG pipelines, evaluation harnesses and scalable AWS infrastructure (Bedrock, SageMaker, Lambda, Step Functions).

• Apply your expertise in frontend technologies such as TypeScript, React, and Next.js to build engaging interfaces, while leveraging Python to develop robust LLM-powered backends and evolving prototypes into reliable, production-ready services.

• Establish automated evals and human-in-the-loop reviews that measure quality, safety and cost efficiency.

• Harvest recurring patterns into platform components (e.g. content-generation pipelines, vector-DB utilities) and document them in our internal playbooks.

• Act as a coach & multiplier - run office hours, code reviews and lightning talks that level-up GenAI skills across idealo.

Skills & Requirements

• Professional software background and 3+ years building production systems; 1+ year hands-on with LLMs.

• Proven experience with LLM stacks: prompt engineering, embeddings & vector DBs , LangChain/LlamaIndex, RAG design, model selection & cost optimisation.

• Practical knowledge of LLM workflow orchestration and process automation tools (e.g., n8n) for end‑to‑end automation.

• Proficient in Python and TypeScript, using modern frameworks like FastAPI, Node.js, and React to create scalable backends and seamless user experiences.

• Comfortable running ML workloads on AWS (SageMaker, Bedrock, Lambda, Step Functions, CDK/Terraform).

• Familiar with CI/CD, Docker, test-driven development and observability (logs, traces, cost dashboards).

• Strong communication skills for pair-programming and technical coaching.

• We’re keen to see evidence of exceptional achievement - perhaps you’ve scaled a personal project to thousands of users, published influential research, ranked highly in competitive arenas (e.g. sports, Kaggle, hackathons) or maintain widely-used open-source libraries. Tell us what makes you stand out!

You don’t tick every single box? No worries! We hire people, not checklists, and value motivation to grow.