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

Datasnipper; Netherlands; On-site; EUR 90,000 - 140,000; Full time

Job summary

Datasnipper seeks a Senior Applied AI Engineer to join the Agent Runtime team behind Alwin, our audit and finance automation platform. You will own the base agents, strategy, and tool integration, shaping how agents reason, manage memory, and interact with the document layer.

This hands-on role demands experience with production-grade AI systems and a focus on reliability and cost efficiency. You will work in a small team with a large blast radius, driving end-to-end development from prototype

Qualifications

• Strong fundamentals in software architecture and system design, with a track record of reliable, well-tested delivery.
• Proficient with AI-assisted engineering and excited about working with coding agents daily.
• Experience shipping and operating an LLM-powered product in production with handling hallucinations, latency spikes, tool failures and cost explosions.
• Hands-on experience building agentic systems: control loops, tool selection, planning vs execution, retries and fallbacks.
• Fluency with LLM APIs and agent frameworks across more than one model provider.
• Experience with evaluation: datasets, offline and online experiments, resulting in measurable AI improvements.
• 5+ years of software engineering experience with strong, production-grade Python.
• Familiarity with OWASP GenAI security practices and working in a regulated, privacy-sensitive environment.
• Sandboxed code execution, MCP, or multi-agent orchestration in production.
• Domain experience in audit, accounting or fintech.
• Experience with RAG and retrieval pipelines over large, messy document corpora.
• Document AI: VLMs, OCR, structured extraction and their metrics.

Responsibilities

• Own the base agents: system prompts, context engineering, memory and state management for long-running tasks.
• Design how agents use the tool layer, including document extraction, retrieval, code and file sandboxes, and MCP integrations.
• Ship end-to-end: from prototype with domain experts, through evaluation, to production on Alwin.
• Define and build automatic processes that improve the agent continuously over time.
• Stay on the frontier: evaluate new models, techniques and agent patterns for production use.
• Partner with Agent Experience, Document Intelligence and AI Platform teams to turn needs into runtime capabilities.
• Keep costs under control and implement cost-efficient AI-centric workflows.

Skills

Software architecture

System design

Agentic systems

LLM APIs

Python

GenAI security

Multi-agent orchestration

RAG

Document AI

Audit domain

Latency optimization

Evaluation

Tools

MCP

Sandboxing

Job description

• We are looking for a Senior Applied AI Engineer to join the Agent Runtime team behind Alwin, our new Agentic Automation Platform for audit and finance


• Alwin agents run for long times, work through multi-step audit procedures over client evidence, and return finished work papers with every number traced back to source


• Humans review and sign off


• The runtime is the layer every agent depends on: the model access, the base system prompt and context, the tools (document extraction, retrieval, sandboxes, MCP integrations), the orchestration of agents and sub-agents, and the observability and evals that tell us whether an agent is performing to objective standards


• You will own the applied AI half of that layer


• Product teams build audit-specific agents on top of it; you decide how the base agent reasons, what tools it gets and at what abstraction, how it manages context over long horizons, and how we measure and hill-climb accuracy, speed and cost


• This is a hands-on role in a small team with a large blast radius


• Your work goes in front of hundreds of thousands of audit and finance professionals, and the problems are largely open: there is no playbook for production agents in a regulated domain, so you will help write it


• Own the base agents: system prompt, context engineering, memory and state management for tasks that span many turns and hours of execution


• Design how agents use the tool layer, including document extraction, retrieval, code and file sandboxes, and MCP integrations, choosing the right level of abstraction so agents handle edge cases without wasting effort on mechanical steps


• Implement agentic patterns such as sub-agent composition, planning modes, human-in-the-loop gates, and model routing across multiple providers


• Ship end-to-end: from prototype with our audit domain experts, through evaluation, to production on Alwin


• Define and build automatic processes that improve the agent continuously over time


• Keep costs under control and implement cost-efficient approaches to AI-centric workflows


• Extract signal from long agent trajectories: attribute outcomes to specific reasoning steps and tool calls, classify failure modes, and turn them into fixes


• Hill-climb accuracy, latency and token cost, and make the trade-offs explicit for the teams building on the runtime


• Instrument agent behaviour with our observability stack and use production traces to drive improvements


• Partner with Agent Experience teams, Document Intelligence and the AI Platform team to turn their needs into runtime capabilities that are self-service rather than a request queue


• Stay on the frontier: evaluate new models, techniques and agent patterns, and bring the ones that hold up into production

Strong fundamentals in software architecture and system design, and a track record of reliable, well-tested deliveryProficient with AI-assisted engineering and excited about working with coding agents dailyExperience shipping and operating an LLM-powered product in production: you have dealt with hallucinations, latency spikes, tool failures and cost explosions at scale, and can explain what broke and how you fixed itHands-on experience building agentic systems: control loops, tool selection, planning versus execution, retries and fallbacks, not only prompt-and-parse pipelinesFluency with LLM APIs and agent frameworks across more than one model providerExperience with evaluation: you have built datasets, run offline and online experiments, and used the results to make an AI system measurably betterExcellent communication; you can work directly with auditors and product partners to define what “correct” means5+ years of software engineering experience with strong, production-grade PythonFamiliarity with OWASP GenAI security practices and working in a regulated, privacy-sensitive environmentSandboxed code execution, MCP, or multi-agent orchestration in productionDomain experience in audit, accounting or fintechExperience with RAG and retrieval pipelines over large, messy document corporaDocument AI: VLMs, OCR, structured extraction and their metricsExperience with Durable workflow engines or long-running background task systems