Minh N.

Senior Python Backend | Agentic AI & LLM | Next.js Frontend Developer

𝐖𝐢𝐭𝐡 𝟏𝟎 𝐲𝐞𝐚𝐫𝐬 𝐨𝐟 𝐬𝐨𝐟𝐭𝐰𝐚𝐫𝐞 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐞𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞: 𝐈 𝐛𝐮𝐢𝐥𝐝 𝐩𝐫𝐨𝐝𝐮𝐜𝐭𝐢𝐨𝐧 AI systems powered by LLMs - agentic workflows (LangGraph, CrewAI), RAG pipelines, and retrieval architectures with hybrid search, vector databases, and guardrails that make them reliable in real-world use. 𝐈 𝐚𝐫𝐜𝐡𝐢𝐭𝐞𝐜𝐭 𝐛𝐚𝐜𝐤𝐞𝐧𝐝 𝐬𝐲𝐬𝐭𝐞𝐦𝐬 that handle concurrency, queues, and scale - async Python services, distributed processing, and data-heavy APIs designed for high throughput and low latency. 𝐈 𝐝𝐞𝐥𝐢𝐯𝐞𝐫 𝐞𝐧𝐝-𝐭𝐨-𝐞𝐧𝐝 𝐟𝐮𝐥𝐥-𝐬𝐭𝐚𝐜𝐤 𝐩𝐫𝐨𝐝𝐮𝐜𝐭𝐬 - from scalable Python backends (FastAPI, Django, Flask) to responsive frontend interfaces (React, Next.js), including real-time features like streaming, WebSockets, and interactive AI UX. 𝐈 𝐫𝐮𝐧 𝐥𝐚𝐫𝐠𝐞-𝐬𝐜𝐚𝐥𝐞 𝐝𝐚𝐭𝐚 𝐩𝐢𝐩𝐞𝐥𝐢𝐧𝐞𝐬 through web scraping and ingestion systems, extracting and normalizing 10k+ items daily across sources, often powering downstream RAG systems and analytics layers. 𝐖𝐇𝐀𝐓 𝐈 𝐃𝐎 𝐁𝐄𝐒𝐓: • Agentic AI/LLM systems with tool use, memory, and deterministic control flows (not just prompt chaining) • Production-grade RAG systems (hybrid search, reranking, pgvector/Qdrant, evaluation loops) • High-performance async python backend APIs (FastAPI/Django), WebSockets, queues, and event-driven architecture • Full-stack product delivery with React/Next.js frontends + Python backends + real-time UX • Large-scale data ingestion & scraping systems with anti-bot handling and normalization pipelines 𝐒𝐓𝐀𝐂𝐊: AI/LLM: OpenAI, Anthropic, AWS Bedrock, LangChain, LangGraph, CrewAI Backend: Python, FastAPI, Django, Flask, async/await Data: PostgreSQL, MongoDB, Redis, Elasticsearch, pgvector, Qdrant Infra: Vercel, AWS, GCP, Docker, Kubernetes Frontend: React, Next.js, TypeScript 𝐇𝐎𝐖 𝐈 𝐖𝐎𝐑𝐊: I clarify constraints early, design for production realities, and ship in small, testable increments. I prioritize correctness, scalability, and maintainability over quick hacks, and I’m direct when scope or architecture doesn’t align with real-world constraints. 𝐁𝐄𝐒𝐓 𝐅𝐈𝐓 𝐅𝐎𝐑: End-to-end AI products, production RAG systems, agentic workflows, async backend systems, scalable full-stack applications, and data-heavy platforms where engineering depth across AI + backend + frontend + data pipelines actually matters.