Working Student AI Software Engineer, LangChain (all genders)

<p style="min-height:1.5em">Thorit GmbH · Böblingen, Germany · Hybrid, mostly on-site · Working student (Werkstudent), 15 to 20 hours per week · Start as early as possible</p><p style="min-height:1.5em"></p><h2><strong>About the Role</strong></h2><p style="min-height:1.5em">You'll build the agent stack an AI consultancy runs on. We use several LLMs across many internal tools, and today each one is wired up differently. You'll turn that into one LangChain foundation: one model-agnostic layer, shared building blocks and proper tracing, then move our internal tools onto it. Real users, real production, from your first month.</p><p style="min-height:1.5em"></p><h2><strong>What You'll Do</strong></h2><ul style="min-height:1.5em"><li><p style="min-height:1.5em"><strong>Map</strong> every internal tool that uses an LLM: which model, how it is called, what data flows through it</p></li><li><p style="min-height:1.5em"><strong>Build</strong> our internal LangChain and LangGraph reference stack with a model-agnostic LLM layer, tool calling, MCP and structured outputs</p></li><li><p style="min-height:1.5em"><strong>Migrate</strong> existing internal tools and agents onto that shared stack</p></li><li><p style="min-height:1.5em"><strong>Compare</strong> LLMs with evals and tracing and help decide which model fits which use case</p></li><li><p style="min-height:1.5em"><strong>Create</strong> templates and docs so colleagues build new tools the same way, including apps that started in Lovable</p></li><li><p style="min-height:1.5em"><strong>Connect</strong> the stack to our systems through APIs, webhooks and a shared data model</p><p style="min-height:1.5em"></p></li></ul><h2><strong>What You Bring</strong></h2><p style="min-height:1.5em"><strong>Must-haves</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Enrolled in a computer science, software engineering, AI, data science or business informatics program</p></li><li><p style="min-height:1.5em">At least one project you built yourself with LangChain or LangGraph (show us the code)</p></li><li><p style="min-height:1.5em">Hands-on experience with more than one LLM or provider and an idea of their trade-offs</p></li><li><p style="min-height:1.5em">Solid Python, plus first experience with REST APIs and SQL</p></li><li><p style="min-height:1.5em">Very good English; German is a plus for working with some internal users</p></li><li><p style="min-height:1.5em">Living close enough to Böblingen to work from our office at least one day a week</p></li></ul><p style="min-height:1.5em"><strong>Nice-to-haves</strong></p><ul style="min-height:1.5em"><li><p style="min-height:1.5em">Experience with LangSmith or other LLM tracing and evals, RAG and vector stores, or MCP</p></li><li><p style="min-height:1.5em">TypeScript and experience with Lovable, Supabase or Postgres</p></li><li><p style="min-height:1.5em">Interest in writing your thesis on an applied LLM or agent topic</p></li></ul><h2><strong>Your Team</strong></h2><p style="min-height:1.5em">You'll report to the