> Markdown version of [/jobs/ext/2729032-ai-llm-engineer](https://www.wearedevelopers.com/jobs/ext/2729032-ai-llm-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI/LLM Engineer - **Company:** Mercura - **Location:** München, Germany - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Information Engineering, Data Systems, Monitoring of Systems, Python (Programming Language), Performance Tuning, Software Deployment, Software Engineering, TypeScript, Unstructured Data, ReactJS, Large Language Models, Multi-Agent Systems, Fastapi, Build Management, Machine Learning Operations, Data Pipelines - **Published:** September 5, 2026 - **Apply:** https://startup.jobs/senior-ai-llm-engineer-mercura-8297843 ## About the Role Technical Skills & Experience: * Proven track record of architecting and building complex, AI/LLM-powered systems or agents in production, including model serving, orchestration of agent workflows, monitoring, and scaling AI workloads * Designing systems that process and structure large volumes of unstructured data * Developing evaluation and feedback loops to measure and improve AI system performance * Experience with Python is required * Experience in full-stack development (React / Typescript / FastAPI) is a plus Mindset & Commitment: * High agency & ownership: You develop new ideas and drive them in execution under minimal guidance * Mission-driven: Your job is part of how you define yourself. You are fully committed to your work and achieving ambitious goals amid uncertainty. * Product mindset: You demonstrate product thinking on a deep level and solve problems end-to-end * You're excited to iterate quickly and build software in a fast-paced startup environment * You want to work in-person in Munich with a higher intensity than in a 9-5 job ## Description As an AI/LLM Engineer, you will play a key role in building agentic AI systems end-to-end. This is a fast-paced, hands-on role for engineers with high agency, strong technical depth and founder mindset. You'll work on building reliable AI systems in production - from retrieval and LLM orchestration to tool-using agents and product integration. If you're a passionate builder who excels at the intersection of LLMs, data systems, AI, data engineering, and full-stack development, this is your opportunity to shape how users interact with AI in real-world workflows. What you will be working on * Agentic Systems: Design and build LLM-powered agentic systems end-to-end, from experimentation to production deployment * Retrieval & Context: Build retrieval and context pipelines (RAG, hybrid search, structured retrieval) to enable reliable reasoning over large volumes of technical and commercial data * AI Evals: Develop evaluation and monitoring systems to measure and improve AI performance in production * Data Pipelines: Build scalable pipelines to process and structure large volumes of unstructured documents and data * Feedback Loops: Implement automated feedback pipelines that allow AI systems to learn from usage data and human feedback * AI Infra: Own the architecture and reliability of AI systems in production, ensuring they are fast, scalable, and robust * Product Integration: Collaborate with other stellar engineers to deeply integrate AI capabilities into the product experience, * Daniel Ribeiro Silva (Senior Director of ML at Nubank, prev. co-founder Hyperplane), For the take-home exercise, we'll provide you with a task. You'll have 3 hours to work with a dataset - exploring the data and developing prediction algorithms using AI engineering methods (e.g., LLMs, embeddings, or retrieval). The challenge is based on a problem we've encountered in our day-to-day work, so it should give you a realistic sense of what the role involves. Afterwards, you'll present your results in a 45-minute session, where we'll discuss your approach, reasoning, and potential improvements. ## Related Videos - [Agentic employees in world's most downloaded FinTech app](https://www.wearedevelopers.com/videos/100123-agentic-employees-in-world-s-most-downloaded-fintech-app) - [Intro to FastAPI](https://www.wearedevelopers.com/videos/462-intro-to-fastapi) - [Watch Tests Go Brrrr! : Getting Started with Cypress in ReactJS](https://www.wearedevelopers.com/videos/282-watch-tests-go-brrrr-getting-started-with-cypress-in-reactjs) - [Do TypeScript without TypeScript](https://www.wearedevelopers.com/videos/327-do-typescript-without-typescript) - [The Intent Engineer: Closing the Gap Between Business & Engineering - Manuel Klein](https://www.wearedevelopers.com/videos/1855-the-intent-engineer-closing-the-gap-between-business-engineering-manuel-klein) - [Building and Deploying Multi-Agent Systems with ADK and Vertex AI](https://www.wearedevelopers.com/videos/1918-building-and-deploying-multi-agent-systems-with-adk-and-vertex-ai) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [The Biggest German Tech Companies](https://www.wearedevelopers.com/magazine/424-the-biggest-german-tech-companies) - [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [The Most Popular IT Jobs on the Market](https://www.wearedevelopers.com/magazine/376-the-most-popular-it-jobs-on-the-market)