{
  "version": 1,
  "updatedAt": "2026-04-02T00:00:00+08:00",
  "site": {
    "name": "Chijun Sima",
    "title": "Chijun Sima",
    "url": "https://www.chijunsima.com/",
    "description": "Chijun Sima — Senior Software Development Engineer at Tencent's WeChat division. Co-first author of Ekko (OSDI 2022). LLVM developer with commit access.",
    "language": "en",
    "llms": {
      "concise": "https://www.chijunsima.com/llms.txt",
      "full": "https://www.chijunsima.com/llms-full.txt"
    }
  },
  "person": {
    "name": "Chijun Sima",
    "givenName": "Chijun",
    "familyName": "Sima",
    "jobTitle": "Senior Software Development Engineer",
    "subtitle": "",
    "employer": {
      "name": "Tencent",
      "department": "WeChat division",
      "url": "https://www.tencent.com"
    },
    "location": "Guangzhou, China",
    "summary": "Co-first author of Ekko (OSDI 2022). LLVM developer with commit access.",
    "email": "simachijun@gmail.com",
    "profiles": {
      "googleScholar": "https://scholar.google.com/citations?user=8-HD_IEAAAAJ&hl=en",
      "linkedin": "https://www.linkedin.com/in/chijun-sima/"
    }
  },
  "education": {
    "period": "Sep 2016 – Jun 2020",
    "startDate": "2016-09",
    "degree": "B.Eng. in Computer Science and Technology (Innovation Class)",
    "school": "South China University of Technology",
    "schoolUrl": "https://www.scut.edu.cn",
    "detail": "GPA 3.85 / 4.00 · Rank 1 / 28"
  },
  "news": [
    {
      "date": "2025-01-01T00:00:00+08:00",
      "dateLabel": "2025",
      "text": "Reviewing for CVPR 2025"
    },
    {
      "date": "2022-09-01T00:00:00+08:00",
      "dateLabel": "2022",
      "text": "Ekko published at OSDI 2022; invited talks at Tencent's WeChat division, DataFun, TechBeat"
    },
    {
      "date": "2022-08-01T00:00:00+08:00",
      "dateLabel": "2022",
      "text": "Tencent Technology Breakthrough Award (Gold Prize) — Project Lead, Ekko"
    }
  ],
  "publications": [
    {
      "id": "ekko-osdi-2022",
      "title": "Ekko: A Large-Scale Deep Learning Recommender System with Low-Latency Model Update",
      "venue": "OSDI '22",
      "venueFull": "16th USENIX Symposium on Operating Systems Design and Implementation",
      "year": 2022,
      "datePublished": "2022",
      "authors": [
        "Chijun Sima",
        "Yao Fu",
        "Man-Kit Sit",
        "Liyi Guo",
        "Xuri Gong",
        "Feng Lin",
        "Junyu Wu",
        "Yongsheng Li",
        "Haidong Rong",
        "Pierre-Louis Aublin",
        "Luo Mai"
      ],
      "authorLine": "Chijun Sima*, Yao Fu*, Man-Kit Sit, Liyi Guo, Xuri Gong, Feng Lin, Junyu Wu, Yongsheng Li, Haidong Rong, Pierre-Louis Aublin, Luo Mai",
      "url": "https://www.usenix.org/conference/osdi22/presentation/sima",
      "note": "* co-first author. Supervised by Luo Mai.",
      "summary": "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."
    },
    {
      "id": "dba-kernel-ieee-access-2019",
      "title": "Dynamic Barycenter Averaging Kernel in RBF Networks for Time Series Classification",
      "venue": "IEEE Access",
      "venueFull": "IEEE Access",
      "year": 2019,
      "datePublished": "2019",
      "authors": [
        "Kejian Shi",
        "Hongyang Qin",
        "Chijun Sima",
        "Sen Li",
        "Lifeng Shen",
        "Qianli Ma"
      ],
      "authorLine": "Kejian Shi, Hongyang Qin, Chijun Sima, Sen Li, Lifeng Shen, Qianli Ma",
      "url": null,
      "note": "2019.",
      "summary": "Time-series classification work on dynamic barycenter averaging kernels in RBF networks."
    }
  ],
  "experience": [
    {
      "period": "Jul 2020 – Present",
      "startDate": "2020-07",
      "role": "Senior Software Development Engineer",
      "subtitle": "",
      "organization": "Tencent's WeChat division",
      "organizationUrl": "https://www.tencent.com",
      "location": "Guangzhou, China",
      "projects": [
        {
          "name": "Ekko: low-latency model update for multi-terabyte DLRMs",
          "note": "published in part as OSDI '22",
          "bullets": [
            "Problem. Scaling DLRMs improved offline accuracy but degraded online engagement; root cause: stale models from increased model-update latency.",
            "Key idea. Co-designed deployment mechanisms with model-aware policies (compressed update dissemination, accuracy-aware scheduling, SLO-aware placement, safe rollback).",
            "Technical contributions. WAN bandwidth −92 %, machine cost −49 %, 2.4 s model-update latency; 10,000× model-size scaling (GB → tens of TB).",
            "Outcomes. Core techniques published as OSDI '22 (co-first author). Deployed in WeChat recommendation stacks, serves 1 B+ users daily. Official WeChat blog reports +40 % DAU and +87 % total VV over six months after full adoption (alongside product iteration and operations)."
          ]
        },
        {
          "name": "Data and feature platform: safe, scalable pipelines",
          "note": null,
          "bullets": [
            "Problem. Modern feature pipelines are long and increasingly multimodal; cross-process operator composition creates high overhead and expensive data movement.",
            "Approach. WebAssembly-based runtime for in-process isolation (safety + resource constraints) and locality-aware operator placement near data sources.",
            "Outcome. Data movement reduced up to 1,200× on representative workloads; widely used within WeChat for data preparation."
          ]
        }
      ]
    },
    {
      "period": "2018 – Present",
      "startDate": "2018",
      "role": "Developer (commit access)",
      "subtitle": "Google Summer of Code 2018",
      "organization": "LLVM",
      "organizationUrl": "https://llvm.org",
      "location": null,
      "projects": [
        {
          "name": null,
          "note": null,
          "bullets": [
            "Improved Semi-NCA performance and optimization pipeline; shipped in LLVM 9.0 (reported speedups up to 1,980× on real-world samples).",
            "Unified APIs on dominator trees; shipped in LLVM 7.0."
          ]
        }
      ]
    }
  ],
  "talks": [
    {
      "text": "Tencent's WeChat division, Shenzhen",
      "date": "Jun 2022"
    },
    {
      "text": "DataFun, Virtual",
      "date": "Aug 2022"
    },
    {
      "text": "TechBeat, Virtual",
      "date": "Sep 2022"
    }
  ],
  "reviewing": [
    "CVPR 2025"
  ],
  "awards": [
    {
      "text": "Tencent Technology Breakthrough Award (Gold Prize) — Project Lead, Ekko (internal highest technical honor)",
      "year": "2022"
    },
    {
      "text": "Bronze Medal, ACM-ICPC Asia Xi'an Regional Contest",
      "year": "2017"
    },
    {
      "text": "Second Prize, 15th China Collegiate Programming Contest (Guangdong Division, out of 177 teams)",
      "year": ""
    }
  ],
  "references": [
    {
      "label": "OSDI 2022 paper",
      "href": "https://www.usenix.org/conference/osdi22/presentation/sima"
    },
    {
      "label": "WeChat official write-up",
      "href": "https://mp.weixin.qq.com/s/gBD3mdoRRlGI8bmXp2OBMA"
    },
    {
      "label": "Tencent official write-up",
      "href": "https://mp.weixin.qq.com/s/hS5ZebOC7oQz_Itud0A_Rg"
    },
    {
      "label": "Synced Review / JIQIZHIXIN",
      "href": "https://mp.weixin.qq.com/s/Vriupgqusj1zJmSuYU9WjA"
    },
    {
      "label": "Google Scholar",
      "href": "https://scholar.google.com/citations?user=8-HD_IEAAAAJ&hl=en"
    }
  ],
  "machineReadableResources": [
    {
      "label": "llms.txt",
      "href": "/llms.txt",
      "type": "text/plain",
      "description": "Concise LLM-oriented summary of the site owner and work.",
      "url": "https://www.chijunsima.com/llms.txt"
    },
    {
      "label": "llms-full.txt",
      "href": "/llms-full.txt",
      "type": "text/plain",
      "description": "Expanded context for deeper agent or retrieval workflows.",
      "url": "https://www.chijunsima.com/llms-full.txt"
    },
    {
      "label": "profile.json",
      "href": "/profile.json",
      "type": "application/json",
      "description": "Machine-readable profile, experience, contact, and links.",
      "url": "https://www.chijunsima.com/profile.json"
    },
    {
      "label": "publications.json",
      "href": "/publications.json",
      "type": "application/json",
      "description": "Selected publications in a clean JSON structure.",
      "url": "https://www.chijunsima.com/publications.json"
    },
    {
      "label": "feed.json",
      "href": "/feed.json",
      "type": "application/feed+json",
      "description": "JSON Feed for site news and notable updates.",
      "url": "https://www.chijunsima.com/feed.json"
    }
  ],
  "canonicalSources": {
    "homepage": "https://www.chijunsima.com/",
    "aiPlugin": "https://www.chijunsima.com/.well-known/ai-plugin.json",
    "sitemap": "https://www.chijunsima.com/sitemap.xml"
  },
  "metadata": {
    "lastUpdated": "2026-04-02",
    "generatedBy": "Astro"
  }
}