Full-Stack Developer Needed: Multi-LLM Subscription-to-API Platform

Job ID: 40464770

Budget: ₹12,500 – ₹37,500 INR

We are looking for an experienced full-stack developer to architect and build a robust platform that converts web account subscriptions into a unified, usable API. The core foundation of this project will utilize the open-source repository sub2api (https://github.com/Wei-Shaw/sub2api).

The platform must act as a seamless bridge, allowing us to route requests to multiple AI models through a single, well-documented API structure.

Key Responsibilities & Technical Requirements:

1. Core Backend & Concurrency:

Implement and extend the sub2api logic to securely manage multiple account sessions.

Design a highly scalable request handler capable of processing heavy concurrent traffic and multi-requests efficiently without dropping connections or triggering rate limits.

2. Multi-LLM Integration:

Integrate multiple AI services into the platform's routing system.

Required integrations include OpenAI (ChatGPT), Anthropic (Claude 3 Opus and Sonnet), and Google (Gemini).

The system must seamlessly switch between these services based on the API endpoint called.

3. Frontend UI/UX (Dashboard):

Build a user-friendly frontend for managing API keys, viewing usage statistics, and monitoring account subscription health.

The design must feature a modern, high-end aesthetic. We are specifically looking for dark mode interfaces (e.g., matte dark emerald backgrounds), clean glassmorphism (glassy UI effects), and subtle, futuristic neon accents.

4. Server Deployment & Infrastructure:

Handle the full production deployment on a Linux VPS.

Configure the environment for 24/7 uptime and automated process recovery using standard process managers such as PM2 and systemd.

Ideal Candidate Profile:

Deep understanding of API design, proxy architectures, and session management.

Strong frontend skills to deliver a premium, dark-themed dashboard.

Solid server administration skills to ensure deployment stability.

How to Apply:
In your proposal, please briefly outline your approach to handling multi-request concurrency for this specific use case. Please also include at least one example of a modern, dark-themed UI/dashboard you have previously built, and mention your experience with process managers for server deployment.