Senior Software Engineer Infra Agent Systems
Together AIVisit Together AI website
Together AI operates an AI-native cloud platform for open and custom AI models.
San Francisco, United States
About Together AI
Together AI provides production AI infrastructure spanning inference, accelerated compute, model training and fine-tuning, and secure code sandboxes for AI development.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build production AI agents that diagnose, investigate, and help remediate infrastructure issues. You will develop distributed services, orchestration, knowledge-graph, retrieval, and fleet-intelligence systems; integrate operational tools through APIs; own services through production operations; and improve agent quality through evaluation and feedback.
Requirements
- 5+ years building production backend systems, distributed systems, or infrastructure platforms
- Systems-design experience and ownership from design through production
- Experience with AI agent systems, knowledge graphs, or search and retrieval systems
- Backend engineering experience with API design, service boundaries, data modeling, and complex integrations
- Experience with Kubernetes, GitOps, infrastructure as code, and cloud platforms
- Experience with Go, TypeScript, Python, or Rust
Responsibilities
- Design and build AI agent systems for infrastructure diagnosis, investigation, and remediation
- Build distributed services, orchestration, knowledge graph, and retrieval systems
- Develop fleet intelligence from telemetry, infrastructure state, operational knowledge, and incidents
- Integrate observability, incident management, ticketing, inventory, source control, chat, and infrastructure systems through APIs
- Own services from architecture through production operations
- Improve agent performance through evaluation, retrieval, tools, and production feedback
- Turn production learning into reviewed software and automation