Applied AI Engineer

Description

The company helps finance teams automate routine work and make better forward-looking decisions.

The company closed a €35 million Series C in August 2026, led by Portage, which put its valuation above €1 billion and made it one of Europe's newer fintech unicorns. Investors include Valar Ventures, Tiger Global, Global Founders Capital, Cherry Ventures and A-Star.

Founded in Berlin, the company serves more than 10,000 businesses, including Flink, Schufa, n8n and Auto1. It has raised over €220 million to date and operates in Germany, the Netherlands, the UK and other EU markets. It offers real-time spend visibility and control through automated card issuing, invoice management and expenses.

The team has more than 300 people from over 50 nationalities across 5 offices in Europe.

You will build AI agents and intelligent product features that change how finance teams work.

This is a product engineering role, not a research or prototyping one. You will take agent features from architecture and evaluation through backend integration, deployment and production operation.

Responsibilities

• Design and build agents that automate complex finance workflows.
• Take features from first concept and prototype through to production.
• Connect agents with backend services, APIs, the data model, permissions and product workflows.
• Design how agents access and use data across the platform in a secure way.
• Turn new AI capabilities into reliable features that customers use.
• Build systematic evaluations covering agent quality, reliability and business impact. This includes test datasets, evaluation criteria, regression tests and human review.
• Measure and improve accuracy, latency, cost and user experience.
• Set up observability and feedback loops so agent behaviour is understandable and can keep improving.
• Apply context engineering methods such as RAG, MCP and knowledge graphs.
• Design prompts, tools, memory, workflows and orchestration for production agents.
• Choose and use orchestration frameworks such as Google ADK, LangGraph, LangChain, LlamaIndex or comparable tools.
• Add guardrails, approval steps and human-in-the-loop controls for sensitive financial workflows.
• Work with data scientists to bring machine-learning models into production systems.
• Build the services, data flows, APIs and operational tooling needed to make models usable in the product.
• Own the production integration yourself instead of passing prototypes to another engineering team.

Requirements

• You are an experienced software engineer who has built and run production applications.
• You are highly proficient in Python and/or Java and work comfortably across backend services, APIs, data and application architecture.
• You have built and shipped at least one agent or LLM-powered product capability from start to finish.
• You have integrated agents into a wider product and backend architecture yourself, not only built standalone prototypes.
• You have hands-on experience evaluating agents or other non-deterministic AI systems.
• You know how to give agents 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 fast experimentation with maintainable, reliable production engineering.
• You communicate clearly and work well with engineering, product and data science colleagues.
• You do not need experience with every technology listed below. Engineering judgment and proven end-to-end ownership matter most.
• 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.

Conditions

Benefits apply to full-time roles. Interns and working students receive a tailored package instead.

The team works in person at the offices, which are central to the company culture.

Benefits

• Top-of-market compensation package, including equity.
• 20 days of work from abroad per year.
• 600 EUR/GBP learning and development budget.
• Other local benefits depending on location.
• Weekly team breakfasts and Friday demos.