Thorit GmbH · Böblingen, Germany · Hybrid, mostly on-site · Working student (Werkstudent), 15 to 20 hours per week · Start as early as possibleAbout the RoleYou'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.
What You'll DoMap every internal tool that uses an LLM: which model, how it is called, what data flows through itBuild our internal LangChain and LangGraph reference stack with a model-agnostic LLM layer, tool calling, MCP and structured outputsMigrate existing internal tools and agents onto that shared stackCompare LLMs with evals and tracing and help decide which model fits which use caseCreate templates and docs so colleagues build new tools the same way, including apps that started in LovableConnect the stack to our systems through APIs, webhooks and a shared data modelWhat You BringMust-havesEnrolled in a computer science, software engineering, AI, data science or business informatics programAt least one project you built yourself with LangChain or LangGraph (show us the code)Hands-on experience with more than one LLM or provider and an idea of their trade-offsSolid Python, plus first experience with REST APIs and SQLVery good English; German is a plus for working with some internal usersLiving close enough to Böblingen to work from our office at least one day a weekNice-to-havesExperience with LangSmith or other LLM tracing and evals, RAG and vector stores, or MCPTypeScript and experience with Lovable, Supabase or PostgresInterest in writing your thesis on an applied LLM or agent topicYour TeamYou'll report to the Team Lead AI Engineering Germany, joining the AI Engineering Germany team within Thorit's AI & Engineering Practice.
Senior engineers set the ar.