Applied AI Engineer

About the job

Responsibilities

• Design and build AI agents to automate complex finance workflows.
• Own features from initial concept and prototype through production deployment.
• Integrate agents with backend services, APIs, data models, permissions, and product workflows.
• Design secure data access mechanisms for agents across the Moss platform.
• Transform emerging AI capabilities into reliable, customer-facing product features.
• Develop systematic evaluations for agent quality, reliability, and business impact.
• Create test datasets, evaluation criteria, regression tests, and human-review processes.
• Measure and improve agent accuracy, latency, cost, and user experience.
• Establish observability and feedback loops for continuous agent improvement.
• Apply context-engineering techniques like RAG, MCP, and knowledge graphs.
• Design prompts, tools, memory, workflows, and orchestration strategies for production agents.
• Select and utilize appropriate orchestration frameworks (e.g., Google ADK, LangGraph, LangChain, LlamaIndex).
• Build guardrails, approval steps, and human-in-the-loop controls for sensitive financial workflows.
• Collaborate with data scientists to integrate machine-learning models into production systems.
• Build necessary services, data flows, APIs, and operational tooling for model integration.
• Take ownership of production integration rather than handing off prototypes.

Requirements

• Seasoned software engineer with experience building and operating production applications.
• Highly proficient in Python and/or Java.
• Comfortable working across backend services, APIs, data, and application architecture.
• Experience building and shipping at least one agent or LLM-powered product capability end-to-end.
• Experience integrating agents into a broader product and backend architecture.
• Practical experience evaluating agents or other non-deterministic AI systems.
• Understanding of providing agents with the right data and context while respecting security, permissions, and privacy.
• Hands-on experience with prompt engineering, context engineering, and agent orchestration.
• Ability to balance rapid experimentation with reliable, maintainable production engineering.
• Clear communication and effective collaboration skills across engineering, product, and data science teams.

Benefits

• Top-of-market compensation package, including equity.
• Vibrant offices fostering collaboration with weekly breakfasts and Friday demos.
• 20 days “work from abroad”.
• 600EUR/GBP Learning & Development Budget.
• Other local benefits.