🤗 Junfan Zhu is an AI Engineer with 5 years of experience in Agentic RL, multi-modal agent reasoning, and scalable LLM/VLM systems. With a strong background in speculative decoding, distributed training, and high-throughput inference, Junfan also brings expertise in multi-agent orchestration, Transformer architectures, mixture-of-experts (MoE), and algorithmic optimization, enabling him to design and scale advanced AI systems end-to-end. He holds Master’s in CS from Georgia Tech and Mathematics from UChicago, and is recognized as a resilient collaborator and builder of high-impact AI systems.

Key Strengths: distributed training (FSDP, MoE), speculative decoding, RAG pipelines, multi-hop reasoning, stochastic optimization, observability, vLLM customization, and high-throughput inference orchestration.

Long-term thinker, resilient collaborator, and builder of high-impact AI systems.

My portfolio boasts pioneering projects in MoE & Attention for scalable LLM, reflective multi-agent orchestrations, and full-stack GenAI applications.

• 1. Awesome-AI-Engineer-Review
  In-depth review of industry trends in AI, LLMs, Machine Learning, Computer Science, and Quantitative Finance.
  • 2025 NVIDIA GTC Conference − Technical & Industrial Insight
  • 2025 Agentic AI Summit Berkeley − Technical & Industrial Insight
• 2. MiniGPT-and-DeepSeek-MLA-Multi-Head-Latent-Attention
  Memory-efficient multi-head latent attention in PyTorch, that leverages low-rank approximation and decoupled rotary positional embeddings, to compress key–value representations, reducing inference memory while maintaining high performance in long-context language models.
• 3. DeepSeek-MoE-Mixture-of-Experts-in-PyTorch
  Implemented scalable 8-expert MoE model with top-k routing, expert load balancing, and capacity-aware gating; enabled parallel sparse activation and DeepSeek-R1-style distributed training scalability.
• 4. MCP-MultiServer-Interoperable-Agent2Agent-LangGraph-AI-System
  A decoupled real-time agent architecture connecting LangGraph agents to remote tools served by custom MCP servers via SSE and STDIO, enabling a scalable multi-agent system for LLM workflows. The design supports flexible multi-server connectivity and lays the groundwork for an Agent2Agent protocol, fostering seamless, cloud-deployable interoperability across diverse AI systems.
• 5. LangGraph-Reflection-Researcher
  Engineered LangGraph-based multi-agent system with self-reflection and retrieval-grounded alignment; integrated LangSmith trace for reasoning introspection, cutting hallucination 40% with iterative expert routing.
• 6. Cognito-LangGraph-RAG-Chatbot
  Advanced Retrieval Augmented Generation (RAG) chatbot that utilizes LangGraph to enhance answer accuracy and minimize hallucinations in LLM outputs.
• 7. Cursor-FullStack-AI-App
  Cursor Vibe Engineering: Full-stack micro SaaS AI application that processes GitHub URLs to generate insightful JSON reports powered by AI analytics.
• 8. Cryptocurrency-Blockchain-FullStack
  Comprehensive decentralized blockchain platform demonstrating practical applications of core blockchain concepts through a modular, full-stack approach.

Favorite project integrating Generative AI, Humanoid Robotics (RLHF), and Low-Altitude Economy.

I’m a traveler ✈️, violinist 🎻, licensed hunter with firearm 🔫 , certified boater ⛵, amateur bartender 🍷 and aspiring private pilot 🚁. My passport has seen more stamps than a post office! 🛂 Having visited 6 continents 🗺️, 60+ countries/regions 🌐, USA 50 states & 50+ national parks 🏞️.

I summited 🇹🇿 Kilimanjaro Uhuru Peak (5895m) at the Roof of Africa 🦒, trekked 🇳🇵 Annapurna Base Camp 🏔, hiked 🇬🇹 Volcán de Fuego 🌋, traversed a desert in 🇨🇳 Inner Mongolia 🏜, and completed 2 marathons (PB within 5h) 🏃.

My expeditions have taken me to beautiful adventurous journeys, such as 🇳🇴 Longyearbyen & Barentsburg (🥶 icebreaker ⛴) in Svalbard 🌌, 🇨🇱 Rapa Nui🗿, 🇨🇦 Iqaluit Nunavut 🐋, 🇦🇷 Ushuaia 🐧, 🇺🇸 Unalaska & Cold Bay in Aleutian Islands🗻 / Utqiaġvik & Prudhoe Bay Alaska ❄️, 🇨🇳 Tibet 🌄, 🇵🇫 Bora Bora 🪸, 🇺🇸 Molokaʻi 🏝️, 🇪🇨 middle of the Earth 🌎 and so on. These experiences have shaped my adaptability 👽, problem-solving skills ✍️, and global perspective 🌊.

📖 Motto: "Every man carries within him a world, composed of all that he has seen and loved, and it is to this world that he constantly returns, even when he seems to be journeying and living in another different world." — Chateaubriand, "Voyages en Italie" 🌅