Website:
frenxt.com
Job details:
WHAT WE'RE BUILDING
We're building an AI-powered coding platform — a browser-based dev environment with an intelligent coding agent that plans, writes code, and iterates autonomously. Users describe what they want; the agent builds it.
Small team, big ambitions. You'll be shipping features that developers interact with daily — not writing JIRA tickets.
THE STACK
Frontend: Next.js 15, React, TypeScript, Zustand, CodeMirror, XTerm.js
API: NestJS, Supabase, Redis, Server-Sent Events
AI Agent: Python 3.11, LangGraph, Anthropic & Google model providers
Infra: Docker, PostgreSQL
Monorepo: Turborepo, pnpm
WHAT YOU'LL WORK ON
→ Agentic AI workflows — Design and improve multi-step agent graphs (LangGraph) that plan, write code, run commands, and self-correct across 33+ tools and 17 skill modules
→ Real-time streaming architecture — SSE pipelines that relay agent actions from Python backend through NestJS to the browser, with reconnection, health monitoring, and interrupt handling (plan approvals, clarifying questions)
→ Browser-based dev environments — Container lifecycle management, file sync, terminal I/O, and live preview — all running in-browser via CodeSandbox SDK
→ State & memory systems — Agent state management with LangGraph checkpointers, middleware-injected context (goals, design docs, memory anchors), and conversation summarization
→ Full-stack product features — Collaboration (roles & permissions), deployment pipelines (Netlify integration), image handling, subscription/quota systems, and onboarding flows
WHAT WE'RE LOOKING FOR
Must-have:
• 5+ years of professional software engineering experience
• Strong TypeScript and Python — you're comfortable shipping production code in both
• Experience with React/Next.js and building complex, stateful UIs
• Familiarity with real-time systems (SSE, WebSockets, streaming APIs)
• You've worked with LLM APIs (Anthropic, OpenAI, Google) beyond just calling a chat endpoint — prompt engineering, tool use, agentic patterns
• Hands-on experience with AI development workflows — building, testing, and iterating on LLM-powered features in production
• Solid understanding of system design — you can reason about how data flows across services
Strong plus:
• Experience with LangGraph, LangChain, or similar agent orchestration frameworks
• Background in developer tools, IDEs, or coding platforms
• Familiarity with container runtimes, sandboxed execution, or browser-based dev environments (CodeSandbox, StackBlitz, Codespaces)
• NestJS or similar Node.js backend framework experience
• Understanding of PostgreSQL, Redis, and Supabase
WHY THIS ROLE IS DIFFERENT
You'll shape the product. This isn't a feature factory. You'll influence architecture, agent behavior, and user experience directly.
AI-native from day one. The AI agent isn't bolted on — it IS the product. You'll work at the intersection of LLM capabilities, developer tooling, and product design.
Depth over breadth. The system spans browser containers, streaming infrastructure, agentic AI, and full-stack web — there's always a hard problem to solve.
Small team, big leverage. Your code ships fast and reaches users immediately. No layers of approval.
HOW TO APPLY
Send us:
1. Your resume or LinkedIn
2. A brief note on what excites you about AI-powered developer tools
3. (Optional) A link to something you've built that you're proud of
Experience: 5+ years | Type: Full-time | Work: Remote-friendly
Click on Apply to know more.