Description

muffintech is at the forefront of AI-driven solutions for the insurance industry, empowering insurance companies to seamlessly integrate cutting-edge technologies into their operations. We are expanding our team and are currently seeking a Machine Learning Engineer to drive innovation in the development and deployment of LLM-based multi-agent systems and intelligent AI workflows. You’ll be working at the intersection of applied research and engineering, shaping the next generation of modular AI applications.

As an ML Engineer at muffintech, you will be instrumental in designing, implementing, and scaling modular multi-agent systems powered by Large Language Models (LLMs). Your work will focus on building reusable AI components and orchestrating intelligent agents that enable automation, insight generation, and decision support across our product ecosystem. You will collaborate with cross-functional teams including product, design, and engineering to bring AI-native workflows to life.

  • Design and implement LLM-powered agents and multi-agent workflows for real-world use cases.
  • Develop tools and infrastructure to support reusable, modular agents that interact via APIs, databases, and user interfaces.
  • Translate complex business logic into flexible, AI-driven systems.

Machine Learning Systems Design

  • Architect and deploy scalable ML pipelines for LLM-based applications.
  • Fine-tune and evaluate foundation models (e.g., GPT, Mistral, LLaMA) for task-specific performance.
  • Optimize inference, latency, and robustness in real-time environments.

AI Workflow & Tooling Integration

  • Build integrations between AI agents and internal tools (e.g., CRMs, document management systems).
  • Develop frameworks for monitoring, evaluating, and debugging AI-driven workflows.

Collaboration & Innovation

  • Work closely with Product and AI Research, to prototype and validate new AI systems and applications.
  • Participate in code reviews, architecture planning, and design sessions.
  • Help shape muffintech’s internal best practices for LLM-based development

  • Strong background in Machine Learning, NLP, or AI systems engineering.
  • Hands-on experience with LLMs, prompt engineering, or fine-tuning transformer-based models.
  • Familiarity with agent frameworks (e.g., LangChain, AutoGen, CrewAI) is a big plus.
  • Solid understanding of Python (FastAPI, PyTorch, HuggingFace), and MLOps best practices.

Working Style & Communication

  • Structured thinking with strong problem-solving skills.
  • Experience working in cross-functional teams and communicating complex ideas clearly.
  • Passionate about building robust AI systems that deliver real value to users

Location: Berlin/remote from germany | Full-time

  • Work on cutting-edge AI systems in a real-world, high-impact domain.
  • A collaborative, innovation-friendly environment where your ideas matter.
  • Flexible work models and a supportive, remote-friendly team culture.
  • Opportunity to shape the future of modular AI in one of the most transformation-ready industries