Senior Applied AI Engineer – Agent Runtime (Alwin by DataSnipper)

The role

You will own the applied AI half of the Agent Runtime layer for the Alwin Agentic Automation Platform. You will design base agents, tool usage, agentic patterns, and evaluation processes to improve accuracy, speed, and cost.

What you will do

• Own base agents including system prompt, context engineering, memory and state management
• Design how agents use the tool layer including document extraction, retrieval, sandboxes, and MCP integrations
• Implement agentic patterns such as sub-agent composition, planning modes, human-in-the-loop gates, and model routing
• Ship end-to-end from prototype to production on Alwin
• Define and build automatic processes to improve the agent continuously
• Keep costs under control and implement cost-efficient approaches
• Extract signal from long agent trajectories to classify failure modes
• Hill-climb accuracy, latency and token cost
• Instrument agent behaviour with the observability stack
• Partner with Agent Experience, Document Intelligence and the AI Platform teams

Required qualifications

• 5+ years of software engineering experience with strong, production-grade Python
• Experience shipping and operating an LLM-powered product in production
• Hands-on experience building agentic systems
• Experience with evaluation including building datasets and running experiments
• Fluency with LLM APIs and agent frameworks across more than one model provider
• Proficient with AI-assisted engineering
• Strong fundamentals in software architecture and system design
• Excellent communication

Nice to have

• Experience with Durable workflow engines or long-running background task systems
• Experience with RAG and retrieval pipelines over large, messy document corpora
• Document AI: VLMs, OCR, structured extraction and their metrics
• Sandboxed code execution, MCP, or multi-agent orchestration in production
• Domain experience in audit, accounting or fintech
• Familiarity with OWASP GenAI security practices and working in a regulated, privacy-sensitive environment

Benefits

• 28 vacation days
• Excellent salary
• Pension plan
• Stock participation plan
• Hybrid work (Amsterdam-based)
• International team and environment
• Daily lunch
• Mental health support (OpenUp)
• Social events and team activities

Before you apply

• Recruiter screen
• Hiring Manager interview
• Peer programming session
• System design interview
• Final interviews with Engineering leadership

About the company

DataSnipper builds AI solutions that empower audit and finance professionals. The company provides an agentic platform called Alwin that allows AI agents to reason across documents with a full audit trail.