Full-Stack Developer for AI Media Generation Platform
Budget: $3,000 – $5,000 USD
Full-Stack Developer Wanted – AI Image & Video Generation Platform
We’re looking for a full-stack developer to build a production-ready AI image & video generation platform. This is not a prototype – we need a stable, scalable system ready for real users.
Core Features
1. User accounts & billing
o Stripe integration (with invoicing support).
o Subscription options: monthly, yearly, one-time bundles, top-ups.
o Configurable per-model costs and quotas.
2. Credits & packages
o Token/credit-based system tied to models.
o Free users can generate limited outputs → their creations are public and displayed in a gallery (Artwork Creations).
3. Generation workflows
o Images: prompt → queue → preview → download.
o Videos: async jobs, webhook/polling, progress tracking, retries, final download.
4. Admin console
o Manage model prices, daily/monthly caps, credits, refunds/compensations.
o Track per-model spend, margins, and user statistics.
5. Content rules
o Respect all provider attributions.
o Never remove or alter watermarks (e.g., SynthID).
6. Storage & CDN
o Store and serve outputs via CDN.
o Auto-cleanup policies for storage management.
7. Analytics & logs
o Usage per user/model, error logs, provider costs.
8. UI/UX & accessibility
o Bilingual interface.
o Light/dark theme switcher.
o Clean, responsive design for desktop & mobile.
Tech Preferences (open to your proposal)
• Frontend: React/Next.js (TypeScript).
• Backend: Node.js (NestJS/Express) or Python (FastAPI).
• Database: Postgres.
• Queue/workers: Redis / Cloud task queue.
• Hosting: major cloud provider with CI/CD.
• Clean architecture, environment-based config, secrets management.
Compliance & Reliability
• GDPR-friendly data handling, cookie consent.
• Respect provider ToS, rate limits, watermarking requirements.
• Robust error handling, exponential backoff, idempotent webhooks.
• Security basics (OWASP), role-based admin access.
Deliverables
• System design (ERD, sequence diagrams, provider API flows).
• Implemented (not prototype) with tests (unit + E2E happy paths).
• Admin panel, billing, credit ledger, and generation flows wired to live APIs.
• Monitoring (health checks, error tracking).
• Bilingual UI, referral codes, couponing, watermark-aware previews, export-to-social.
• Dynamic pricing rules (margin-based), downloadable usage reports.
• Documentation + knowledge transfer session.
APIs to Integrate
• Gemini Imagen, Nano Banana, OpenAI, Leonardo AI, Artlist AI, Pollo AI
Candidate Screening – Please answer concisely:
1. Relevant experience: links to AI generation platforms or API integrations you’ve built (esp. Gemini, OpenAI, Leonardo, Pollo, Artlist, Nano Banana).
2. Proposed stack & architecture: your rationale for frontend, backend, queue, storage, and CDN.
3. Async video jobs: how would you handle job status, webhooks, retries, and partial failures?
4. Cost control: how to track provider spend per request, enforce rate limits, and prevent runaway costs?
5. Security & compliance: GDPR, secrets, multi-tenant safety, watermarking requirements.
6. Timeline & availability: your estimated duration.
7. Handover quality: how you provide tests, docs, and short admin training at the end.
If this matches your skills, please reply with a short Loom video or written outline of your approach.
We’re looking for a full-stack developer to build a production-ready AI image & video generation platform. This is not a prototype – we need a stable, scalable system ready for real users.
Core Features
1. User accounts & billing
o Stripe integration (with invoicing support).
o Subscription options: monthly, yearly, one-time bundles, top-ups.
o Configurable per-model costs and quotas.
2. Credits & packages
o Token/credit-based system tied to models.
o Free users can generate limited outputs → their creations are public and displayed in a gallery (Artwork Creations).
3. Generation workflows
o Images: prompt → queue → preview → download.
o Videos: async jobs, webhook/polling, progress tracking, retries, final download.
4. Admin console
o Manage model prices, daily/monthly caps, credits, refunds/compensations.
o Track per-model spend, margins, and user statistics.
5. Content rules
o Respect all provider attributions.
o Never remove or alter watermarks (e.g., SynthID).
6. Storage & CDN
o Store and serve outputs via CDN.
o Auto-cleanup policies for storage management.
7. Analytics & logs
o Usage per user/model, error logs, provider costs.
8. UI/UX & accessibility
o Bilingual interface.
o Light/dark theme switcher.
o Clean, responsive design for desktop & mobile.
Tech Preferences (open to your proposal)
• Frontend: React/Next.js (TypeScript).
• Backend: Node.js (NestJS/Express) or Python (FastAPI).
• Database: Postgres.
• Queue/workers: Redis / Cloud task queue.
• Hosting: major cloud provider with CI/CD.
• Clean architecture, environment-based config, secrets management.
Compliance & Reliability
• GDPR-friendly data handling, cookie consent.
• Respect provider ToS, rate limits, watermarking requirements.
• Robust error handling, exponential backoff, idempotent webhooks.
• Security basics (OWASP), role-based admin access.
Deliverables
• System design (ERD, sequence diagrams, provider API flows).
• Implemented (not prototype) with tests (unit + E2E happy paths).
• Admin panel, billing, credit ledger, and generation flows wired to live APIs.
• Monitoring (health checks, error tracking).
• Bilingual UI, referral codes, couponing, watermark-aware previews, export-to-social.
• Dynamic pricing rules (margin-based), downloadable usage reports.
• Documentation + knowledge transfer session.
APIs to Integrate
• Gemini Imagen, Nano Banana, OpenAI, Leonardo AI, Artlist AI, Pollo AI
Candidate Screening – Please answer concisely:
1. Relevant experience: links to AI generation platforms or API integrations you’ve built (esp. Gemini, OpenAI, Leonardo, Pollo, Artlist, Nano Banana).
2. Proposed stack & architecture: your rationale for frontend, backend, queue, storage, and CDN.
3. Async video jobs: how would you handle job status, webhooks, retries, and partial failures?
4. Cost control: how to track provider spend per request, enforce rate limits, and prevent runaway costs?
5. Security & compliance: GDPR, secrets, multi-tenant safety, watermarking requirements.
6. Timeline & availability: your estimated duration.
7. Handover quality: how you provide tests, docs, and short admin training at the end.
If this matches your skills, please reply with a short Loom video or written outline of your approach.