Call for Engineer

🚀 Hermes Web: Call for Founding Engineer

Hermes Web is looking for a founding engineer to build the first polished, hosted personal AI agent product.

Some facts about us:

Incubated by Open Core Ventures, the studio founded by Sid Sijbrandij (ex-CEO of GitLab)

Building the hosted, non-technical-user version of Hermes Agent — the fastest-growing open-source agent framework after OpenClaw

OCV underwrites infrastructure and LLM costs, so you optimize for growth and polish, not unit economics

Fully remote, product-focused, compressed sprint cadence

If you want to own product and engineering end-to-end, ship consumer-grade polish in a space that's still raw, and help define what a mainstream AI agent product looks like, this is for you.

Project described below.

Requirements

High agency, ship fast without hand-holding

Strong Python skills — FastAPI or similar production web framework experience required

Strong frontend skills (React, Next.js, TypeScript) for the chat, memory, and activity surfaces

Experience with auth, billing, and multi-tenancy in production products

Container orchestration experience (Kubernetes, Nomad, ECS, or equivalent)

Experience with AI-native tools (Cursor, Claude Code, model APIs)

Knowledge of agents, LLM gateways, rate limiting, and abuse prevention

Comfortable working across frontend, backend, infrastructure, and AI workflows

The kind of person we want: someone who has shipped a consumer or prosumer product they're still proud of, and who responds to an aggressive timeline with "tight but doable if we cut X, Y, Z" rather than "let me spec it first."

Bonus skills:

Experience with agent frameworks (Hermes, OpenClaw, LangGraph)

LLM gateway or proxy work

Stripe subscription billing at scale

Production experience hardening agentically-generated code

OSS contributions

Consumer AI product experience (Cowork, Cursor, or similar)

Project: Hosted Hermes Agent Platform

1. Introduction

We are building a multi-tenant hosted platform that gives anyone their own personal Hermes agent running in the cloud in under 60 seconds. No terminal, no API keys, no configuration. The agent persists, remembers them, and gets better over time.

This project includes:

Per-user Hermes containers with network and storage isolation

A warm pool provisioning system for instant signup-to-first-message

A production-hardened chat, memory, and activity interface

An LLM gateway that meters usage, enforces caps, and prevents abuse

Bundled Claude Sonnet access — users never see an API key or model selector

Stripe billing infrastructure and self-serve subscription flows

2. Requirements

Platform and provisioning

Per-tenant container orchestration via Kubernetes or Nomad

Warm pool pattern for sub-90-second provisioning

Idle sleep and fast wake (under 2 seconds on incoming message)

Persistent per-tenant memory and conversation storage

Auth via Clerk or Auth0 (email + Google OAuth, email verification required)

Frontend

React, Next.js, TypeScript, Tailwind, shadcn

Multi-tenant chat, memory, and activity surfaces

Graceful handling of connection loss, agent timeouts, container restarts

Streaming responses, conversation history, new-thread flows

LLM gateway

Proxy every Anthropic API call from every tenant container

Hold Anthropic API keys server-side; tenant containers never see them

Per-tenant metering with second-by-second granularity

Hard daily and monthly cost caps

Circuit breakers for runaway loops

Ops kill switch for any tenant

Billing and ops

Stripe subscription integration at $20/mo

Self-serve upgrade, downgrade, cancel

Internal ops dashboard for user management and anomaly response

Runbooks for common failure modes

3. Non-Goals

Developer-facing platform

Self-hosted desktop or mobile apps

Skills marketplace or plugin ecosystem

Workflow builder, triggers, scheduled agents

Team accounts, SSO, enterprise features

Multiple LLM providers or model selection

Bring-your-own API key

Forking Hermes — we track upstream and contribute back

4. Prior Art

Hermes Agent — the open-source framework we build the hosted experience on top of

OpenClaw — the largest agent framework today and reference for community patterns and growth dynamics

LangGraph Deep Agents — architecture patterns for stateful long-running agent workflows

Anthropic MCP — server design patterns for tool interfaces and permission-aware context

Cowork (Anthropic) — polish bar and UX patterns for non-technical AI agent products

Cursor agent UI — interaction model for AI agents in consumer products