Agentic Builder - Claude Code
Built around Claude Code and multi-agent workflows; explicitly rejects 'vibe-coders' and requires deep, under-the-hood agent engineering.
About the Role
Build production applications by orchestrating Claude Code and other coding agents; design skills, manage context and memory, and ship working software on a per-project basis. Deliver end-to-end solutions including CI/CD, deployments, databases, security, and agent-driven TDD, with builders typically earning $10k+ per month.
Job Description
Role
Agentic Builder working with Claude Code to deliver production software on a per-project basis. You will orchestrate agents, author skill and prompt artifacts, manage long-running context and memory, enforce quality through agent-driven TDD and reviews, and handle deployments, databases, and security for shipped apps.
Key Responsibilities
- Take projects from specification to deployed software with Claude Code and other coding agents doing most of the typing.
- Author CLAUDE.md files, skills, and prompt systems that produce consistent output.
- Manage context, sub-agents, memory, and token usage across long-running tasks.
- Drive TDD with agents using hooks, sub-agents, and verification patterns; ensure agents do not cheat.
- Set up CI/CD, deployments, databases, secrets, and monitoring.
- Act as the final quality gate: review, refactor, and ship production-ready code.
Requirements
- Real, demonstrable Claude Code experience; shipped production apps (not POCs or toys).
- Multi-agent fluency (experience with Cursor, Codex, Copilot, Amp, Cline, or similar) and ability to articulate trade-offs.
- Skill authoring experience (SKILL.md, system prompts, agent definitions) producing reusable outputs.
- Context engineering and memory management (external memory, RAG, file-system memory, structured handoffs).
- Token-economy optimization and model selection awareness.
- Strong Git skills (branches, rebases, worktrees, conflict resolution) and code-reading/debugging ability.
- Deployment experience (Next.js → Vercel; backends → Fly, Railway, AWS; containers) and operational debugging.
- Postgres-class database fluency (Supabase, Neon, RDS, PlanetScale): schemas, indexes, migrations, RLS.
- Security best practices: secrets management, auth flows (OAuth, JWT), input validation, CORS, prompt injection mitigation, scoped tool permissions, OWASP Top 10 awareness.
- Networking and infra basics: DNS, HTTPS, environment isolation, observability (logs, error tracking, uptime monitoring).
- TDD and testing (unit/integration): pytest, Jest, Vitest, Playwright or equivalent, plus eval frameworks for agent quality.
- Clear communication and ownership: proactive flagging of issues and thoughtful code review.
Benefits / Compensation
- $10,000+ per month (paid per project) with uncapped upside for operators who ship multiple projects.
- Per-project structure with defined scope and deliverables.
- Fully remote, async-friendly work.
- High autonomy: choose agent architecture, skills, and workflows.
- Steady pipeline and repeat work for consistent deliverers.
- Direct access to decision-makers; minimal layers.
- Tooling budget for model APIs, plugins, and required infrastructure.
- Peer network of top-tier agentic operators.