Infra AI Engineer: Build Self-Improving Production Agents

Matcha; Northern (KY); Hybrid; USD 250,000 - 300,000; Full time

Benefits offered by this job

Remote work flexibility

Job summary

Together AI is seeking a skilled engineer to help scale production backend systems that power a massive GPU fleet. You will contribute to two areas: Infrastructure Agent Systems and Core Agent Platform, building knowledge graphs, retrieval, and orchestration that enable self-improving AI agents.

You will own end-to-end services, work across Go, TypeScript, Python, or Rust, and shape solutions across infrastructure, telemetry, and automation with real production impact.

Qualifications

• 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 at least one: AI agent systems, knowledge graphs, search/retrieval/semantic search.
• Strong backend engineering experience, including API design, service boundaries, data modeling, and integrations across complex systems.
• Experience with Kubernetes, GitOps such as ArgoCD, infrastructure-as-code, and cloud platforms.
• Comfortable working across languages such as Go, TypeScript, Python, or Rust.

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, operational knowledge, and historical incidents to help agents make better decisions.
• Integrate with observability, incident management, ticketing, fleet inventory, source control, chat, and internal infrastructure systems through well-designed APIs.
• Own services end to end, including architecture, implementation, testing, deployment, observability, and production operations.
• Improve agent performance through evaluations, retrieval improvements, better tools, and production feedback loops.
• Turn what agents learn in production into reliable, reviewed software and automation.

Skills

Backend systems design

Distributed systems

API design

Kubernetes

GitOps (ArgoCD)

Cloud platforms

Go

TypeScript

Python

Rust

Tools

Kubernetes

ArgoCD

Prometheus

Grafana

Kafka

NATS

Graph databases

Job description

Together AI is seeking a skilled engineer to help scale production backend systems that power a massive GPU fleet. You will contribute to two areas: Infrastructure Agent Systems and Core Agent Platform, building knowledge graphs, retrieval, and orchestration that enable self-improving AI agents.

You will own end-to-end services, work across Go, TypeScript, Python, or Rust, and shape solutions across infrastructure, telemetry, and automation with real production impact.