Open to opportunities

Kaiven Zhou

@kaivenzhou

Senior AI/Machine Learning engineer specializing in LLMs, RAG, and large-scale personalization and recommendation systems.

United States

Message

What I'm looking for

I seek senior roles building production-scale ML and GenAI systems—focus on LLMs, personalization, ranking, and reliable MLOps—collaborative, product-driven teams.

I am a Senior AI/Machine Learning Engineer with a decade of experience building and shipping production ML and GenAI systems at scale for consumer and marketplace products. I specialize in LLMs, Retrieval-Augmented Generation, agentic and multi-agent AI systems, embeddings and hybrid search, personalization, ranking, and end-to-end ML pipelines that support hundreds of millions of users.

I have delivered measurable business impact through LLM-driven feature pipelines, unified learn-to-rank frameworks, GenAI-personalized homepages, anomaly and fraud detection platforms, and production GNNs. I focus on reproducible, containerized workflows, cost-aware GPU inference, robust monitoring and evaluation, and close cross-functional collaboration to translate complex product problems into reliable, high-impact AI solutions.

Experience

Work history, roles, and key accomplishments

Current

Senior AI/Machine Learning Engineer

Current

DoorDash

Aug 2021 - Present (4 years 7 months)

Architected and productionized LLM-driven retrieval and recommendation systems (RAG, embeddings, hybrid search) that improved personalization and relevance, delivering 4–5% lifts in AUC/MRR and ~30% higher carousel trigger rates while scaling to hundreds of millions of users.

LLM RAG Embeddings Hybrid Search Ranking Personalization Spark Airflow Docker

Senior Machine Learning Engineer

Facebook

Jan 2019 - Jul 2020 (1 year 6 months)

Developed large-scale ranking, personalization, and integrity ML systems (multi-task learning, embeddings, fake-engagement detection) that reduced low-quality impressions and improved relevance across Feed, Stories, and Ads.

Ranking Embeddings Fraud Detection Content Moderation Spark Airflow Docker A B Testing

Machine Learning Engineer

Microsoft

Jul 2015 - Dec 2018 (3 years 5 months)

Built and deployed search and personalization ML (CV/NLP, embeddings, ONNX runtime) for Bing and Office, shipping vision and NLP models for Visual Search and PowerPoint Designer with Azure-based GPU inference and reproducible pipelines.

Computer Vision NLP Embeddings ONNX Runtime Azure Deep Learning A B Testing

Education

Degrees, certifications, and relevant coursework

Columbia University

Bachelor of Science, Operations Research

2011 - 2015

Completed a Bachelor of Science in Operations Research with coursework and projects focused on quantitative modeling, optimization, and decision analysis.