Jesse Zhang
Founder & CEO at Niantic, Inc.
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolJesse Zhang is a founder and engineering leader based in San Francisco with a decade of experience building product-driven startups and engineering teams, currently serving as Founder & CEO of Lowkey (YC) and working on social products at Niantic after Lowkey's acquisition. He combines deep practical knowledge of front-end technologies like React, CSS and WebGL with backend and ML tooling experience—contributing to prominent open-source LLM tooling such as LlamaIndex and community data loaders for LLMs. Jesse has a strong quantitative background from a fast-tracked CS degree at Harvard and early internships across top firms in finance and tech, which inform his interest in financial markets and deep learning. He’s particularly focused on tooling and pipelines for document ingestion and multimodal data processing, having added parsers, metadata handling, and image captioning to widely used projects. Comfortable oscillating between product strategy and hands-on engineering, he often ships features that bridge research prototypes and production systems. Avidly curious, he explores TFT and Web3 experiments on the side, blending systems thinking with creative UI and graphics work.
10 years of coding experience
Computer Science, Graduated in 3 years, Computer Science, Graduated in 3 years at Harvard UniversityMOP x2, RSI, Intel STS Finalist, SPARC, USACO, MOP x2, RSI, Intel STS Finalist, SPARC, USACO at Fairview High School
befunge, Chinese, English
Github Skills (16)
file-handling10
application-framework10
app-framework10
web-framework10
data-loading10
lm10
file-parsing10
python10
webscraping10
data-processing10
llm10
pdf-parsing9
document-processing9
parsing9
parse9
Programming languages (8)
Github contributions (5)
run-llama/llama-hub
Jan 2023 - Mar 2023
A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
Role in this project:
Backend Developer
Backend DeveloperContributions:99 reviews, 119 commits, 67 PRs in 1 month
Contributions summary:Jesse implemented core functionalities related to data loading and processing for LLMs. Their contributions included defining base schemas for documents, creating a directory reader for various file types, and integrating readers for specific file formats like PDF, DOCX, and PPTX. They also added web page readers and a reader for arxiv papers, showcasing an understanding of data acquisition and transformation pipelines for language models.
run-llama/llama_index
Jan 2023 - Mar 2023
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Role in this project:Back-end Developer
Back-end DeveloperContributions:24 reviews, 13 commits, 16 PRs in 2 months
Contributions summary:Jesse contributed to the `SimpleDirectoryReader` class, adding functionalities like file metadata handling and the ability to limit the number of files read. They also modified the `GPTIndexInserter` and `BaseGPTIndex` classes to include and utilize metadata within Document nodes, integrating it with the file reader. Additionally, the user added a pptx parser and image captioning capabilities. These changes indicate involvement in data loading, document processing, and index creation functionalities within the LlamaIndex framework.
basesindexknowledgeframeworkllm
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.