Senior AI Agent Infra & Platform Engineer

Socket.dev; San Francisco (CA); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Startup equity

Health insurance

Flexible remote work

Job summary

Together AI is building the Infra Agent Systems that power and automate a massive GPU fleet. You will create production AI agents to diagnose failures, investigate incidents, and automate remediation, while also developing the platform for knowledge graphs, retrieval, and orchestration.

You’ll work to make agents trustworthy in production and build the foundational systems that enable self-improving AI agents to operate at scale across infrastructure and automation tasks.

Qualifications

• 5+ years of experience building production backend systems and distributed platforms.
• Strong systems design skills and ownership of large-scale systems.
• Depth in AI agent systems, knowledge graphs, search, or related areas.
• Backend engineering experience including API design and cross-system integrations.

Responsibilities

• Design and build production AI agent systems that diagnose, investigate, and remediate infrastructure issues across one of the world’s largest GPU fleets.
• Build the distributed services, orchestration framework, knowledge graph, and retrieval systems that power infrastructure agents.
• Develop fleet intelligence systems that combine telemetry, infrastructure state, and historical incidents to aid decision making.
• Integrate with observability, incident management, ticketing, inventory, source control, chat, and internal systems via APIs.
• Own services end to end: architecture, implementation, testing, deployment, observability, and production operations.
• Improve agent performance through evaluations, retrieval improvements, and production feedback loops.
• Turn what agents learn in production into reliable, reviewed software and automation.

Skills

Backend engineering

Distributed systems

API design

Systems design

Designing scalable services

Tools

Kubernetes

ArgoCD

IaC tools

Go

TypeScript

Python

Rust

GitOps

Job description

Together AI is building the Infra Agent Systems that power and automate a massive GPU fleet. You will create production AI agents to diagnose failures, investigate incidents, and automate remediation, while also developing the platform for knowledge graphs, retrieval, and orchestration.

You’ll work to make agents trustworthy in production and build the foundational systems that enable self-improving AI agents to operate at scale across infrastructure and automation tasks.