Open to opportunities

Michael Zhu

@michaelzhu

Message

Senior Full Stack AI Engineer building end-to-end LLM, NLP, and RAG systems that ship reliably to production.

United States

Message

What I'm looking for

I’m looking for a fast-paced team where I can build end-to-end LLM/NLP and RAG systems with real ownership—shipping scalable full-stack services, optimizing performance, and creating reusable components for production-grade automation.

I’m an innovative Full Stack AI Engineer with 8+ years of experience building and deploying AI-powered applications, LLM-based systems, and scalable full-stack platforms in fast-paced environments. I bring strong ownership mindset and focus on delivering end-to-end solutions—from ideation to production—with emphasis on performance, reliability, and user experience.

In my current role, I designed and deployed end-to-end AI-powered applications integrating LLMs, NLP, and agentic workflows using LangChain and LangGraph. I built scalable RAG-based systems with FAISS, Pinecone, and pgvector, improving retrieval accuracy by 40%, and reduced manual workload by 55% through intelligent automation for summarization, search, and decision-making.

I’ve also delivered real-time NLP and enterprise conversational AI using LangChain and backend APIs, improving model performance and application reliability by 25% through optimization, debugging, and evaluation pipelines. Across teams, I build reusable, modular AI components and production-ready backend APIs and frontend integrations, while optimizing throughput by 30% using asynchronous processing and microservices architecture.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Engineer

Current

Alluxii

Jun 2023 - Present (3 years)

Designed and deployed end-to-end AI-powered applications using LangChain and LangGraph, building RAG systems with FAISS, Pinecone, and pgvector to improve retrieval accuracy by 40%. Reduced manual workload by 55% via intelligent automation and increased throughput by 30% using asynchronous processing and microservices architecture.

Lang Chain LangGraph RAG Architecture Faiss Pinecone Pgvector Microservices Architecture Redis CI CD

Senior AI Engineer

DivIHN

Mar 2019 - Jun 2023 (4 years 3 months)

Built and deployed NLP-driven applications and enterprise conversational AI using LangChain and backend APIs, enabling real-time AI interactions and automation workflows. Improved model performance and application reliability by 25% through optimization, debugging, and evaluation pipelines.

Natural Language Processing (NLP)Lang Chain Conversational AI Data Pipelines Model Evaluation Debugging Reliability Engineering

Software Engineer Intern

DivIHN

Sep 2018 - Feb 2019 (5 months)

Developed LLM, semantic search, and multimodal AI pipelines, building real-time backend systems with sub-200ms latency using Redis Streams, WebRTC, and distributed architecture. Implemented FAISS-based semantic search to improve recommendation quality and user experience.

LLM Semantic Search REDIS Streams WebRTC Distributed Architecture Faiss Recommendation Systems