Want to know if this job is worth applying to?
Berlin, Deutschland
Hybrid
At Moss, we give finance professionals the power to automate their day-to-day and make forward-thinking decisions.
Our culture is what makes that possible: we play to win, we obsess over quality, and we win as One Moss, and it works. Moss closed a €35 million Series C in August 2026, crossing a €1 billion valuation, and became one of Europe's fintech unicorns. Join us for what's next.
We are hiring an Applied AI Engineer to build AI agents and intelligent product capabilities that transform how finance teams work.
This is a product engineering role - not an isolated prototyping or research role. You will own agent-based features end to end: from architecture and evaluation through backend integration, deployment, and operation in production.
Build and Ship AI Agents
Design and build agents that automate complex finance workflows.
Own features from initial concept and prototype through production deployment.
Integrate agents deeply with our backend services, APIs, data model, permissions, and product workflows.
Design how agents securely access and use data from across the Moss platform.
Turn emerging AI capabilities into reliable, customer-facing product features.
Evaluate and Improve Agent Performance
Build systematic evaluations for agent quality, reliability, and business impact.
Create representative test datasets, evaluation criteria, regression tests, and human-review processes.
Measure and improve accuracy, latency, cost, and user experience.
Establish observability and feedback loops that make agent behavior understandable and continuously improvable.
Develop the AI Application Architecture
Apply context-engineering techniques such as RAG, MCP and knowledge graphs.
Design prompts, tools, memory, workflows and orchestration strategies for production agents.
Select and use appropriate orchestration frameworks, such as Google ADK, LangGraph, LangChain, LlamaIndex, or comparable technologies.
Build appropriate guardrails, approval steps, and human-in-the-loop controls for sensitive financial workflows.
Integrate Machine-Learning Capabilities
Collaborate with data scientists to integrate machine-learning models into our production systems.
Build the services, data flows, APIs, and operational tooling required to make models usable within the product.
Take responsibility for the production integration rather than handing prototypes to another engineering team.
You are a seasoned software engineer with experience building and operating production applications.
You are highly proficient in Python and/or Java and comfortable working across backend services, APIs, data, and application architecture.
You have built and shipped at least one agent or LLM-powered product capability end to end.
You have personally integrated agents into a broader product and backend architecture - not only developed standalone prototypes.
You have practical experience evaluating agents or other non-deterministic AI systems.
You understand how to provide agents with the right data and context while respecting security, permissions, and privacy.
You have hands-on experience with prompt engineering, context engineering, and agent orchestration.
You balance rapid experimentation with reliable, maintainable production engineering.
You communicate clearly and collaborate effectively across engineering, product, and data science.
Relevant Technologies
You do not need experience with every technology below. We care most about strong engineering judgment and demonstrated end-to-end ownership.
Agent orchestration: Google ADK, LangGraph, LangChain, LlamaIndex, or comparable frameworks
Context engineering: RAG, MCP, knowledge graphs, tool use, memory, and retrieval systems
AI evaluation: offline and online evaluations, test datasets, regression testing, observability, and human review
Language models: Gemini, OpenAI, Anthropic, Llama, Mistral, or similar
Backend engineering: Python or Java, REST APIs, Kafka, microservices, and distributed systems
Data systems: SQL, PostgreSQL, BigQuery, vector search, and data pipelines
Cloud AI platforms: GCP and Vertex AI, or comparable platforms
About Moss
Moss is the Finance AI platform for Europe's mid-sized businesses, giving companies real-time visibility and full control over their spend. By automating card issuing, invoice management and expenses, Moss simplifies financial workflows and frees finance and accounting teams from manual, administrative work.
Founded in Berlin and used by more than 10,000 businesses including Flink, Schufa, n8n and Auto1, Moss has raised €220+ million to date and operates in Germany, the Netherlands, the UK and further EU markets. In August 2026, Moss closed a €35 million Series C led by Portage, crossing a €1 billion valuation and becoming one of Europe's newest fintech unicorns. Moss is backed by investors including Valar Ventures, Tiger Global, Global Founders Capital, Cherry Ventures, A-Star.
We're a team of 300+ people from 50+ nationalities across 5 offices in Europe and we hire, reward, and grow people based on Moss DNA: playing to win, obsessing over quality, winning as One Moss. If that's how you want to work, we want to hear from you. - here's what else to expect:
Top-of-market compensation package, including equity.
Our vibrant offices are at the heart of our culture, where in-person time fuels collaboration and connection over weekly breakfasts and Friday demos.
Additional benefits include: 20 days “work from abroad”, 600EUR/GBP Learning & Development Budget, and other local benefits.
Unless stated otherwise, benefits apply to full-time positions (interns and working students receive a tailored package).
By applying for the above position, you will confirm that you have reviewed and agreed to our Data Privacy Policy.
