LLM Prompting | React/Next.js | GPT-4/Claude | Express/NestJS | RAG Systems | FastAPI | LLM Optimization | No-code automation | PyTorch | Expo
1. LLM & Prompt Engineering
Frameworks: LangChain, LlamaIndex, OpenAI API, Anthropic Claude, Mistral, Leonardo.ai, Gemini, ManyChat
Prompting: Chain-of-Thought, Few-Shot, ReAct, Tool-Use, Self-Critique
RAG: Pinecone, Weaviate, pgvector, Chroma, Neo4j
Fine-Tuning: LoRA, QLoRA, GGUF quantization
Evaluation: LLM Judge, ROUGE, BLEU, Custom Metrics
2. Web Integration
Backend: Express, NestJS, FastAPI, AWS Lambda, Supabase, Firebase
Frontend: Next.js (App Router), Vercel AI SDK, React Streaming, Vue.js
APIs: REST, GraphQL, WebSockets (real-time chat)
Auth: JWT, OAuth, NextAuth.js
3. Deployment & Scalability
Infra: Docker, Kubernetes, Serverless (Vercel/AWS)
Performance: Redis caching, Rate Limiting, CDN (Cloudflare)
Security: PII redaction, CSP Headers, Prompt Injection Defense
4. Machine Learning
Classic ML (Scikit-learn, XGBoost for hybrid systems)
NLP Basics (SpaCy, NLTK, Regex)
Computer Vision (OpenCV, TorchVision - for multimodal apps)
5. No-Code Automation (Optional)
Tools: Make.com, Zapier, n8n, Airtable
LLM Triggers: OpenAI API + Slack/Shopify/Telegram/WhatsApp