Senior Software Engineer — Infra Agent Systems
$250k - $300k • Remote • San Francisco
Posted 24d ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
Together AI runs one of the largest GPU fleets globally, and the Infra Agent Systems team is responsible for developing the software that powers and automates this infrastructure. The team builds production AI agents designed to diagnose hardware failures, investigate incidents, correlate signals across the fleet, and automate operational workflows. Alongside these agents, they are building the core platform, which includes knowledge graphs, retrieval systems, orchestration frameworks, and developer tooling. This role offers the unique opportunity to work at the intersection of AI agents, distributed systems, infrastructure, and automation, tackling complex engineering challenges with significant real-world impact.
Responsibilities
- Design and build production AI agent systems for diagnosing, investigating, and remediating infrastructure issues.
- Develop distributed services, orchestration frameworks, knowledge graphs, and retrieval systems for infrastructure agents.
- Create fleet intelligence systems that combine telemetry, infrastructure state, and historical data for better agent decision-making.
- Integrate with observability, incident management, ticketing, and other internal infrastructure systems via APIs.
- Take ownership of services end-to-end, including architecture, implementation, testing, deployment, and operations.
- Enhance agent performance through evaluations, retrieval improvements, and feedback loops.
- Translate learnings from production agents into reliable software and automation.
Requirements
- 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.
- Depth in AI agent systems, orchestration, tool use, evaluation, or grounding.
- Depth in knowledge graphs or graph data modeling.
- Depth in search, retrieval, ranking, RAG, or semantic search systems.
- Strong backend engineering experience, including API design, service boundaries, and data modeling.
- Experience with Kubernetes, GitOps (e.g., ArgoCD), infrastructure-as-code, and cloud platforms.
- Comfortable working with languages such as Go, TypeScript, Python, or Rust.
Benefits
- Competitive compensation
- Startup equity
- Health insurance
- Flexibility in terms of remote work