Job
In this role, you will develop an AI agent platform focusing on multi-tenant architecture, eval frameworks, and RAG pipelines. You will handle auditing and integrate modern tools and frameworks.
This listing has been machine translated. Show original
Job technologies
Your role in the team
- A production-ready AI agent platform built on PydanticAI, LiteLLM, and Langfuse.
- RAG pipelines with pgvector at scale: multi-tenant isolation, index rebuild strategy, hybrid search, and re-ranking.
- A multi-tenant token quota service and evaluation frameworks per tenant.
- MCP tool integration (Model Context Protocol) as an integral part of the architecture.
- End-to-end auditability from prompt to output, ensuring decisions are traceable for business teams and regulators.
- Architecture decisions that stand up to scrutiny in banking, insurance, and pharmaceutical environments.
Our expectations of you
Qualifications
- 5+ years of software engineering with Python in production.
- RAG systems that you have built and operated yourself, including retrieval tuning and re-ranking.
- An agent framework such as LangGraph, PydanticAI, or a comparable solution in production.
- Very good German and good English, as you will be working with enterprise customers in the DACH region.
- pgvector sizing for large datasets.
- Kubernetes fundamentals.
Experience
- Experience with LLMs in production: tokens, latency, costs, and evals are part of your everyday work.
- A plus, but not a must: experience with LiteLLM, Langfuse, or MCP. You’ll quickly learn anything you’re not familiar with yet.
- Experience with regulatory requirements such as the EU AI Act, DORA, BaFin/MaRisk, or GxP.
What we offer
- Responsibility from day one: You shape the agent architecture instead of just tuning prompts, with no management layer above you.
- Direct line: You report to Christoph Knöll (Founder/CEO) and work closely with our Head of AI, with short decision-making paths.
- Flexibility: Fully remote from anywhere in Germany, flexible working hours, with team days at the Munich office approximately once a month.
- Room to experiment: A modern stack and the time to seriously evaluate new models, frameworks, and retrieval approaches.
- Professional exchange: A team that runs LLM systems in production and makes decisions based on evals.
- Professional development and visibility: conferences, training, and the opportunity to represent the company externally as an expert, for example through talks or specialist articles.
Benefits
Health, fitness & fun
Work-Life-Integration
Topics you will work on
Job locations
About your employer
Neurawork is a strategic AI consulting firm focused on the German-speaking mid-sized companies. The company combines consulting, technical expertise, and transformation skills to assist clients in implementing practical AI solutions.
- Startup
- Onsite, Hybrid, Full Remote
- Consulting
More jobs
These jobs might also interest you
Hello, let's say WE! We - the HUK-COBURG Insurance Group - are among the top 10 in Germany. Founded over 90 years ago, we are now the leading insurer for private households with over 13 million customers and the largest German auto insurer. Our...
You actively shape the technical development of our software products and influence their long-term architecture. You develop our core applications primarily using C# as the central programming language and technological foundation. You design, develop,...
The role As a Forward Deployed AI Engineer, you go directly into our specialist departments, understand the processes, and develop production-ready AI and automation solutions that will fundamentally change the way the entire GGW Group operates. You do...