【27届校招】Data Infra工程师(向量检索)
上海、广州、北京
正式
研发 - 算法
职位描述
1、建设十亿~百亿级向量的生产管线:批量提取 embedding 的高吞吐推理链路,覆盖增量数据的每日流入、版本管理与质量校验; 2、建设与优化向量检索引擎:ANN 索引(IVF/HNSW/DiskANN 等)的选型、调优与自研扩展,向量量化(PQ/SQ/二值化)与降维(PCA/MRL)在召回与成本间的权衡,标量-向量混合检索的执行路径优化; 3、深入列式存储与数据湖格式(Lance/Parquet 等)底层,参与我们 Lance 分支的开发:存储布局、索引结构、增量写入下的索引实时性、大规模标量过滤(bitmap/B-tree/倒排)等; 4支撑上层数据挖掘与 curation 场景:为密度分析、长尾挖掘、多向量精排(late interaction)等提供高性能的底层能力,与算法同学共建从粗召回到精排的完整检索链路。
职位要求
1、2027届硕士应届毕业生,计算机科学与技术、电子工程、通信工程、自动化等相关专业; 2、扎实的系统编程能力,熟练 Rust/C++/Python 之一,有独立排查性能问题的经验; 3、理解向量检索的原理而不止于调用,熟悉至少一种向量检索系统(Faiss/Milvus/Qdrant/LanceDB 等)的内部机制,或有列式存储、数据库内核、搜索引擎相关开发经验; 4、有真实的大规模数据处理经验(亿级行 / TB 级以上),对容量估算和量级账敏感。 加分项 1、参与过开源向量数据库、数据湖格式(Lance/Arrow/Parquet)或数据库内核的开发; 2、有 GPU 加速检索(Faiss-GPU/RAFT/cuVS)或大规模 embedding 推理优化经验; 3、熟悉 ColBERT 类 multi-vector 检索的工程化(存储压缩、两段式召回精排; 4、有自动驾驶、推荐、搜索等亿级以上向量场景的落地经验。
投递

XPeng is a leading Chinese Smart EV company that designs, develops, manufactures, and markets Smart EVs that appeal to the large and growing base of technology-savvy middle-class consumers. Its mission is to drive Smart EV transformation with technology and data, shaping the mobility experience of the future. In order to optimize its customers’ mobility experience, XPeng develops in-house its full-stack advanced driver-assistance system technology and in-car intelligent operating system, as well as core vehicle systems including powertrain and the electrical/electronic architecture. XPeng is headquartered in Guangzhou, China. In 2021, the Company established its European headquarters in Amsterdam, along with other dedicated offices in Copenhagen, Munich, Oslo, and Stockholm.The Company’s Smart EVs are mainly manufactured at its plant in Zhaoqing and Guangzhou,Guangdong province.
For more information, please visit https://heyxpeng.com.