Francisco De Haro
Full Stack Developer · Next.js · AI & ML
Contact
Profile
Full-stack developer with 3 years of experience in own products and freelance. Specialized in Next.js, React Native and AI integration in production. App published on App Store with subscriptions and complete backend. Experience in code auditing and bug resolution in large codebases (+300K lines). Immediate availability.
What I bring
- Technical consulting and bug resolution in production
- iOS/Android mobile apps with Expo and React Native
- Production AI API integration (LLMs, image generation)
- Payments and subscriptions: Stripe, RevenueCat, App Store Connect
Remote · EU timezone. Open to freelance projects, technical collaborations, or positions where I can build product from day one.
Projects
2025Live
- Stripe Connect & Split Payments: Implementation of connected accounts
- Multi-tenant Management: Database architecture in Supabase
- Webhooks & Synchronization: Robust payment event listening system
- Dynamic Pricing Algorithm (Tiered Pricing) for commissions
- Retention Engine (Churn Prevention) for subscriptions
Next.jsStripe ConnectSupabasePostgreSQLTailwind CSSFintech
Repai Trainer↗
iOS Mobile App Development (Fullstack)
apps.apple.com/us/app/repai-trainer/id67497651392025Live
- 100+ users · Organic content with 30K views
- Personalized workout generation with OpenAI API
- Subscription system (monthly, annual, lifetime) with RevenueCat
- Exercise database integrated with Gymvisual
- Progress tracking and statistics
ExpoReact NativeSupabasePostgreSQLRevenueCatApp Store
2025Live
- +21,400 answers · +1,600 questions · 100% organic growth
- Creation and management of personalized multiple-choice exams
- Integrated AI chat with OpenAI for assistance while answering
- User system with Supabase Auth
- PostgreSQL database to store exams and answers
Next.jsOpenAISupabasePostgreSQLEdge FunctionsTypeScript
Llama Fine-tuning for Spanish Lyrics
Fine-tuning Llama 3.3 and 3.1 models for music lyrics generation
2024
- Fine-tuning Llama 3.3 (1B/3B) and 3.1 (8B) with QLoRA 4-bit
- Custom dataset of +10,000 prompt-completion examples
- Autonomous scraping pipeline with Playwright for capture and parsing
- Intelligent tokenization with masking (labels=-100 in prompts)
- Optimized training with Unsloth (~2× faster)
PyTorchLlamaFine-tuningQLoRAHugging FaceUnsloth
Tech Stack
Frontend & Mobile
Next.jsReactTypeScriptExpoReact NativeXcodeTailwind CSS
Backend & Database
Node.jsTypeScriptSupabaseDrizzle ORMNeonPostgreSQL
Auth & Payments
ClerkStripeRevenueCatApp Store Connect
AI & Machine Learning
LLMsAPIs de modelosPyTorchFine-tuningLoRAQLoRAStable DiffusionHugging Face
DevOps & Tools
VercelCloudflareGitHubCI/CDCoolifyCursorClaude Code
Education
Business Administration Degree — Universidad de Murcia (in progress)
Languages
Spanish
Native
English
Advanced
French
Basic
Available immediately for collaborations and new opportunities.
Contact → frandeharo55@gmail.com