Senior Infrastructure Engineer

About us

Manufact builds dev-tools and cloud infrastructure for MCP and software used by AI agents.

Our platform helps teams build, deploy, test, and distribute MCP servers and apps across ChatGPT, Claude, Muse, Grok Bot, and other AI agents.

• Why now: MCP is becoming the most important product surface for every company.
• Growth: Tool calls on our infra +38% WoW since June (there's a live counter on our website).
• Open source: We created mcp-use SDK (Next.js for MCP) for building MCP Apps with 10k Github stars and 10M+ downloads.
• Backed by the best: Y Combinator (S25) and raised a $6.3M seed round led by Peak XV, with investors including the founders of Supabase.
• Our goal: A big portion of global MCP tool calls will run on Manufact.

We believe every software company will need an agent interface, just as it needs a website today.

What you'll do

• Build the cloud platform that hosts customer MCP servers with millions of tool calls.
• Set up monitoring, observability, and dashboards across every MCP server on Manufact Cloud and the full stream of events and logs we ingest, so problems surface before users feel them.
• Build alerting and error handling that flags threshold breaches and failures in real time.
• Make sure the platform scales as we add thousands of users and capture a growing share of global AI tool calls.
• Create the tooling and technical blueprints that let customers deploy Manufact into their own private clouds (AWS, Azure, GCP) on their own terms.
• Build the security boundaries that keep each customer's data private and isolated within their own environment.
• Own where our code lives and how it ships: code hosting and the release pipeline.
• Keep the system fast and reliable as companies add more MCP servers.

Requirements

• You have built and operated cloud systems end-to-end and know them inside out.
• Experience standing up the observability stack that keeps a cloud healthy: logs, metrics, traces, dashboards, and alerting at scale.
• Kubernetes or Terraform, and containerized multi-tenant systems.
• Comfortable being the first person to own infrastructure at a fast-growing startup.
• Based in or willing to relocate to San Francisco.

Nice to have

• Hands-on with observability tooling such as ClickHouse, Prometheus, OpenTelemetry, Grafana.
• Experience running a platform that others deploy onto (PaaS-flavored).