Applied AI Engineer

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.

Your Responsibilities

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.