Founding Engineer (AI)

TL;DR

Founding Engineer (AI): Building a multi-tenant hosted personal AI agent platform with an accent on per-user container orchestration, warm pool provisioning, and production-hardened chat interfaces. Focus on designing LLM gateways for metering and abuse prevention, integrating Stripe billing, and ensuring instant signup-to-first-message experience.

Location: Fully remote

Company

Incubated by hirify.global, the studio founded by ex-CEO of GitLab, building the hosted non-technical-user version of Hermes Agent open-source framework.

What you will do

• Own end-to-end product and engineering from frontend chat surfaces to backend infrastructure and AI workflows
• Implement per-tenant container orchestration with Kubernetes or Nomad and warm pool for sub-90-second provisioning
• Build production chat, memory, and activity interfaces with React, Next.js, TypeScript handling streaming and connection loss
• Develop LLM gateway proxying Anthropic API calls with per-tenant metering, cost caps, and circuit breakers
• Integrate Stripe for $20/mo subscriptions with self-serve flows and build internal ops dashboard
• Ensure persistent memory, auth via Clerk/Auth0, and fast wake from idle sleep

Requirements

• High agency and ability to ship fast without hand-holding
• Strong Python skills with FastAPI or similar production web framework experience
• Strong frontend skills in React, Next.js, TypeScript
• Experience with auth, billing, multi-tenancy in production
• Container orchestration experience (Kubernetes, Nomad, ECS)
• Experience with AI-native tools, agents, LLM gateways, rate limiting, abuse prevention

Nice to have

• Experience with agent frameworks (Hermes, OpenClaw, LangGraph)
• LLM gateway or proxy work
• Stripe subscription billing at scale
• Production hardening of agentically-generated code
• OSS contributions
• Consumer AI product experience (Cowork, Cursor)

Culture & Benefits

• Fully remote with product-focused compressed sprint cadence
• OCV underwrites infrastructure and LLM costs for growth optimization
• End-to-end ownership in early-stage AI agent space