jobapplier

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

Datasnipper

Skills

Required

  • LLM-powered
  • hallucinations
  • latency spikes
  • tool failures
  • building agentic systems
  • control loops
  • tool selection
  • planning
  • retries
  • fallbacks
  • prompt-and-parse
  • LLM APIs
  • agent frameworks
  • Python

Preferred

  • code execution / MCP / multi-agent orchestration in
  • RAG
  • retrieval pipelines
  • document corpora
  • VLMs
  • OCR

Join DataSnipper as a Senior Applied AI Engineer, where you'll be at the forefront of developing Alwin, our innovative Agentic Automation Platform for audit and finance. In this hands-on role, you'll own the applied AI layer that every agent depends on, design how agents use the tool layer, and implement agentic patterns. You'll also ship end-to-end, define and build automatic processes for continuous improvement, and stay on the frontier of AI advancements.

Posséder la moitié appliquée de la couche d'exécution des agents, en prenant des décisions sur la manière dont l'agent de base raisonne, les outils qu'il utilise et comment il gère le contexte.

About Datasnipper

  • Experience with evaluation: you have built datasets, run offline and online experiments, and used the results to make an AI system measurably better
  • Excellent communication; you can work directly with auditors and product partners to define what "correct" means

Responsibilities

  • Concevoir et mettre en œuvre des modèles d'agents, y compris la composition de sous-agents, les modes de planification, les portes humaines dans la boucle et le routage des modèles.
  • Collaborer avec les équipes de produit pour définir et construire des processus automatiques qui améliorent continuellement l'agent au fil du temps.
  • Strong fundamentals in software architecture and system design, and a track record of reliable, well-tested delivery

Requirements

  • Proficient with AI-assisted engineering and excited about working with coding agents daily
  • 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
  • Hands-on experience building agentic systems: control loops, tool selection, planning versus execution, retries and fallbacks, not only prompt-and-parse pipelines
  • Fluency with LLM APIs and agent frameworks across more than one model provider
  • 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
  • Experience with Durable workflow engines or long-running background task systems

Preferred

  • 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