# Chijun Sima

> Senior Software Development Engineer at Tencent (WeChat). ML systems researcher focused on efficient AI, model freshness, recommender systems, and LLM serving. Co-first author of Ekko (OSDI 2022). LLVM developer with commit access.

Last updated: 2026-03-15

- Website: https://www.chijunsima.com/
- Email: simachijun@gmail.com
- Google Scholar: https://scholar.google.com/citations?user=8-HD_IEAAAAJ&hl=en
- GitHub: https://github.com/NutshellySima
- LinkedIn: https://www.linkedin.com/in/chijun-sima/
- CV (PDF): https://www.chijunsima.com/cv.pdf

## Flagship work

**Ekko: A Large-Scale Deep Learning Recommender System with Low-Latency Model Update** (OSDI '22): Low-latency model update system for multi-terabyte deep learning recommendation models, achieving 2.4s update latency, 10,000x model-size scaling, and large production impact in WeChat.

Paper: https://www.usenix.org/conference/osdi22/presentation/sima

## Research areas

Machine Learning Systems, MLSys, Efficient AI, Model Freshness, Recommender Systems, Deep Learning, Deep Learning Recommendation Models, LLM Serving, KV-Cache Management, WebAssembly, LLVM, Compilers, Distributed Systems

## Machine-readable endpoints

- llms.txt: https://www.chijunsima.com/llms.txt (Concise LLM-oriented summary of the site owner and work.)
- llms-full.txt: https://www.chijunsima.com/llms-full.txt (Expanded context for deeper agent or retrieval workflows.)
- profile.json: https://www.chijunsima.com/profile.json (Machine-readable profile, experience, contact, and links.)
- publications.json: https://www.chijunsima.com/publications.json (Selected publications in a clean JSON structure.)
- feed.json: https://www.chijunsima.com/feed.json (JSON Feed for site news and notable updates.)

## Canonical page

Chijun Sima — ML systems researcher at Tencent (WeChat). Research on efficient AI systems, model freshness, recommender systems, and LLM serving. Co-first author, OSDI 2022 (Ekko). LLVM developer with commit access.