Senior Software Engineer (Infra Agent Systems)

Join our team as a Senior Software Engineer (Infra Agent Systems) and work on two challenging problems: making AI agents trustworthy for production infrastructure and building the systems that make those agents effective. You will have the opportunity to build foundational systems from the ground up, work on infrastructure at massive scale, and help define how self-improving AI agents operate real-world AI infrastructure.

Responsibilities

• Your responsibilities will include designing and building production AI agent systems, developing fleet intelligence systems, integrating with various internal systems, and improving agent performance.
• Conception et construction de systèmes d'agents d'IA de production pour diagnostiquer, enquêter et remédier aux problèmes d'infrastructure.
• Développement de systèmes d'intelligence de flotte qui combinent la télémétrie, l'état de l'infrastructure, les connaissances opérationnelles et les incidents historiques.
• Intégration avec des systèmes d'observabilité, de gestion des incidents, de billetterie, d'inventaire de flotte, de contrôle de source, de chat et d'infrastructure interne.
• Search, retrieval, ranking, RAG, or semantic search systems

Knowledge graphs or graph data modeling

• Strong backend engineering experience, including API design, service boundaries, data modeling, and integrations across complex systems
• Comfortable working across languages such as Go, TypeScript, Python, or Rust
• Observability platforms such as Prometheus and Grafana

Requirements

Depth in at least one of the following

• Experience with Kubernetes, GitOps such as ArgoCD, infrastructure-as-code, and cloud platforms
• AI agent systems, orchestration, tool use, evaluation, or grounding
• 5+ years of experience building production backend systems, distributed systems, or infrastructure platforms
• Strong systems design skills and experience owning significant systems from design through production
• Building evaluation frameworks or improving the quality and reliability of LLM-powered systems
• Event-driven systems and messaging platforms such as NATS or Kafka
• Graph databases
• GPU infrastructure, datacenters, bare-metal systems, hardware failure modes, BMC/IPMI, or cluster schedulers

Pay

USD 250,000 - 300,000