Senior AI Engineer, Agent Runtime & Trustworthy Automation

Datasnipper; Amsterdam; Hybrid; EUR 110,000 - 160,000; Full time

Benefits offered by this job

Hybrid work (Amsterdam-based)

28 vacation days

Pension plan

Stock participation plan

Daily lunch

Mental health support (OpenUp)

Social events and team activities

Job summary

DataSnipper is seeking a Senior Applied AI Engineer to join the Agent Runtime team and shape the Alwin platform. You will own the applied AI layer, defining how base agents reason, what tools they access, and how context is managed across long horizons.

You will work with product teams to build audit-specific agents that are explainable and traceable to sources. The role is hands-on in a small team with a large impact: you’ll help write playbooks for production agents in regulated domains and

Qualifications

• 5+ years of software engineering experience in production
• Experience shipping and operating an LLM-powered product
• Hands-on experience building agentic systems
• Proficient with AI-assisted engineering and evaluating AI systems

Responsibilities

• Own the base agents: system prompt, context engineering, memory and state management
• Design how agents use the tool layer (extraction, retrieval, sandboxes, MCP)
• Implement agentic patterns: sub-agent composition, planning modes, human-in-the-loop gates
• Ship end-to-end: prototype to production on Alwin
• Define and build automatic processes that improve agent over time
• Keep costs under control and optimize AI-centric workflows
• Instrument agent behaviour with observability and production traces
• Collaborate with other teams to turn needs into runtime capabilities
• Evaluate new models and agent patterns for production use

Skills

Python

LLM APIs

Agentic systems

Software architecture

Production AI

Tools

Sandboxed code

MCP integrations

Retrieval pipelines

Job description

DataSnipper is seeking a Senior Applied AI Engineer to join the Agent Runtime team and shape the Alwin platform. You will own the applied AI layer, defining how base agents reason, what tools they access, and how context is managed across long horizons.

You will work with product teams to build audit-specific agents that are explainable and traceable to sources. The role is hands-on in a small team with a large impact: you’ll help write playbooks for production agents in regulated domains and