Applied AI Engineer

Salary: £63,000 - 103,000 per year

Requirements:

• We are looking for a seasoned software engineer with experience building and operating production applications.
• We expect you to be highly proficient in Python and/or Java and comfortable working across backend services, APIs, data, and application architecture.
• You must have built and shipped at least one agent or LLM-powered product capability end to end.
• You must have personally integrated agents into a broader product and backend architecture, not only developed standalone prototypes.
• We are looking for practical experience evaluating agents or other non-deterministic AI systems.
• You should understand how to provide agents with the right data and context while respecting security, permissions, and privacy.
• You should have hands-on experience with prompt engineering, context engineering, and agent orchestration.
• You should balance rapid experimentation with reliable, maintainable production engineering.
• You should communicate clearly and collaborate effectively across engineering, product, and data science.
• Relevant experience with technologies such as Google ADK, LangGraph, LangChain, LlamaIndex, RAG, MCP, knowledge graphs, offline and online evaluations, observability, human review, Gemini, OpenAI, Anthropic, Llama, Mistral, Python or Java, REST APIs, Kafka, microservices, distributed systems, SQL, PostgreSQL, BigQuery, vector search, data pipelines, GCP, and Vertex AI is helpful, but not required.

Responsibilities:

• We build and ship AI agents that automate complex finance workflows.
• We own features from initial concept and prototype through production deployment.
• We integrate agents deeply with our backend services, APIs, data model, permissions, and product workflows.
• We design how agents securely access and use data from across the Moss platform.
• We turn emerging AI capabilities into reliable, customer-facing product features.
• We build systematic evaluations for agent quality, reliability, and business impact.
• We create representative test datasets, evaluation criteria, regression tests, and human-review processes.
• We measure and improve accuracy, latency, cost, and user experience.
• We establish observability and feedback loops that make agent behavior understandable and continuously improvable.
• We apply context-engineering techniques such as RAG, MCP, and knowledge graphs.
• We design prompts, tools, memory, workflows, and orchestration strategies for production agents.
• We select and use appropriate orchestration frameworks, such as Google ADK, LangGraph, LangChain, LlamaIndex, or comparable technologies.
• We build guardrails, approval steps, and human-in-the-loop controls for sensitive financial workflows.
• We collaborate with data scientists to integrate machine-learning models into our production systems.
• We build the services, data flows, APIs, and operational tooling required to make models usable within the product.
• We take responsibility for production integration rather than handing prototypes to another engineering team.

Technologies:

• AI
• AI Agents
• BigQuery
• Backend
• Flink
• GCP
• Java
• Kafka
• LLM
• MCP
• PostgreSQL
• Python
• RAG
• REST
• SQL
• Security
• microservices
• Cloud
• Excel

More:

We are Moss, the Finance AI platform for Europes mid-sized businesses, giving companies real-time visibility and full control over their spend. By automating card issuing, invoice management, and expenses, we simplify financial workflows and free finance and accounting teams from manual, administrative work. Founded in Berlin and used by more than 5,000 businesses including Flink, Schufa, Gusto, and Auto1, we have raised 200+ million to date and operate in Germany, the Netherlands, the UK, and further EU markets. We are backed by renowned tech investors including Valar Ventures, Tiger Global, Global Founders Capital, Cherry Ventures, A-Star, and Portage. Our team includes 300+ people from 50+ nationalities across 5 offices in Europe. We offer a top-of-market compensation package including equity, vibrant offices with weekly breakfasts and Friday demos, 20 days work from abroad, a 600 EUR/GBP Learning & Development Budget, and other local benefits. This is a full-time hybrid role based in Warsaw, Berlin, or London, within our EPD department, and benefits apply to full-time positions unless stated otherwise.

last updated 36 week of 2026