Founding Engineer

Jinba lets enterprise teams vibe-code AI workflows instead of drag and drop. Describe what you need in plain language, and your whole company can start using it immediately. No engineers required. Enterprise-grade permissions, audit logging, and on-prem deployment built in. We serve 40,000+ daily enterprise users at major financial institutions including Fortune Global 500 companies in banking, insurance, and manufacturing.

Full-stack engineer who understands vibe coding tools and how recent AI frameworks work. You'll build both frontend and backend for our enterprise workflow automation platform.

• Architect and build both frontend and backend systems powering our vibe coding platform
• Define technical strategy: system design, data modeling, service boundaries, and infrastructure choices
• Integrate AI models and build reliable natural language to action pipelines
• Collaborate directly with customers to translate enterprise needs into product solutions
• Evolve infrastructure for reliability, observability, and performance at enterprise scale
• Ship fast while building sustainable, maintainable systems

Experience

• 5+ years building products quickly
• TypeScript (backend and frontend), React
• Deep understanding of system design, database architecture, and scaling distributed systems
• Modern deployment and infrastructure (Vercel, Cloudflare Workers). Infrastructure as code (Terraform). CI/CD pipelines (GitHub Actions)
• Experience with AI frameworks (Vercel AI SDK, Mastra) and patterns (agentic loops, tool calling, streaming, MCP)

Bonus

• Understanding of tools like OpenCode and how they work
• Shipped AI/LLM products to production.
• LLM observability and production debugging (Langfuse, Datadog).
• Experience at early-stage startups
• Major contributions to OSS projects

Mindset

• Founder mentality: hard work, independence, ownership
• Ready to work in person in San Francisco

Jinba is a vibe-coding platform that compiles natural language into production-grade workflow code, deployed instantly as APIs, MCP servers, webhooks, or cron jobs. The core challenge is constrained code generation for the enterprise: translating ambiguous business intent into deterministic, auditable execution graphs that integrate with arbitrary enterprise systems (Salesforce, SAP, internal APIs), all while enforcing compliance constraints at the code generation level. Errors here have real financial consequences. On the infra side, we serve 40,000+ daily users at Fortune Global 500 companies, which means multi-tenant isolation with on-prem deployment, sub-second workflow execution, audit-grade observability, and hybrid AI model orchestration across AWS Bedrock, Azure AI, OpenAI, and self-hosted models. Our frontend is modern React with shadcn/ui, and we're one of the earliest platforms treating MCP as a first-class deployment target. If you want to work on problems at the intersection of AI, compilers, and enterprise infrastructure, we're hiring.