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

Join DataSnipper, the Agentic Automation Platform for audit and finance, as a Senior Applied AI Engineer. In this hands-on role, you will own the applied AI layer of our Agent Runtime, designing how agents use the tool layer, implementing agentic patterns, and continuously improving the agent over time. You will work directly with auditors and product partners, ship end-to-end from prototype to production, and stay on the frontier of AI technology.

- Posséder la responsabilité de la couche d'exécution des agents, y compris l'accès aux modèles, le prompt système, l'ingénierie du contexte, la gestion de la mémoire et de l'état. - Concevoir et mettre en œuvre des processus automatiques qui améliorent continuellement l'agent au fil du temps, en gardant les coûts sous contrôle et en mettant en œuvre des approches rentables. - Collaborer avec les équipes d'expérience des agents, d'intelligence documentaire et de la plateforme d'IA pour transformer leurs besoins en capacités d'exécution qui sont en libre-service.

- Excellent communication; you can work directly with auditors and product partners to define what "correct" means - Strong fundamentals in software architecture and system design, and a track record of reliable, well-tested delivery - 5+ years of software engineering experience with strong, production-grade Python - Hands-on experience building agentic systems: control loops, tool selection, planning versus execution, retries and fallbacks, not only prompt-and-parse pipelines - Experience 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 it - Experience with evaluation: you have built datasets, run offline and online experiments, and used the results to make an AI system measurably better - Proficient with AI-assisted engineering and excited about working with coding agents daily - Fluency with LLM APIs and agent frameworks across more than one model provider - Familiarity with OWASP GenAI security practices and working in a regulated, privacy-sensitive environment - Domain experience in audit, accounting or fintech - Document AI: VLMs, OCR, structured extraction and their metrics - Sandboxed code execution, MCP, or multi-agent orchestration in production - Experience with RAG and retrieval pipelines over large, messy document corpora - Experience with Durable workflow engines or long-running background task systems