Find a jobRecruiters

算法工程师(供应链销量预测)

Exclusive opportunity

Onsite

算法工程师(供应链销量预测)

沃尔玛(中国)投资有限公司

算法工程师(供应链销量预测)

Skills

SQL QueriesPythonNumPypandasMySQLLinuxHadoop

2 months ago

Share this opportunity

Share this opportunity to other talents of your network:
✓ Offer them a visibility boost with clients.
✓ Help your contacts find their next job.

Important information


Contract type:

Permanent

Location:

Shenzhen, Guangdong Province, China

Work mode:

Onsite

Published on:

17 August 2026

What they need


该职位来源于猎聘 岗位职责: 1. 负责多层次(品类/单品/仓端等不同粒度)商品销量预测的研发,支持门店/云仓/中心仓订单量预测(如提前 N 天预测),构建精准的供应链需求预测模型,支撑生产计划、排班及库存优化决策; 2. 结合商品自身属性,融合节假日、促销活动、天气等外部特征,构建鲁棒、可解释的预测模型,提升复杂场景下的预测稳定性; 3. 持续研究并引入业界的时序预测方法(如 TFT、TimesFM、Chronos等深度时序模型),推动其在零售供应链场景中的规模化落地; 4. 深入理解业务场景,协同供应链、生产、物流等部门进行全链路分析,将预测结果与下游计划、库存策略有效衔接,推动算法落地与策略迭代; 5. 建立预测算法的科学评估体系,通过历史回测、灰度发布验证模型有效性,持续跟踪并优化预测精度; 任职要求: 1. 计算机、数学、统计学等相关专业,硕士及以上学历,有互联网或零售行业相关工作经验者优先; 2. 熟练掌握 Python,能够熟练使用 NumPy、Pandas、Scikit-Learn 独立完成建模实验;熟悉 Linux 基础命令; 3. 熟练掌握 SQL,熟悉 Hadoop/Hive/MySQL 等数据工具,具备 Spark 大数据处理经验者优先; 4. 熟悉常见机器学习模型及原理,如 LR、Boosting、Bagging、PCA 等,熟练掌握分类、回归、聚类等常用算法,熟悉 LightGBM、XGBoost 等工程应用中的关键调参,具备大规模机器学习/数据挖掘项目经验;有深度学习经验、尤其是应用过深度时序模型者优先; 5. 热爱预测算法、具备主动学习与钻研精神,参与过 Kaggle M5 Forecasting 等相关竞赛或活跃于相关技术社区者优先。

Other offers great for you!

These companies are also looking for great profiles

AMRG

Expert(e) Oracle - Performance & Tuning

50 - 60 K€ (selon profil et expérience)

Permanent contract

Vannes, France

Hybrid, Onsite

Skills

SQL QueriesOracle DatabaseAnsibleLinuxOracleWindows

14 hours ago

Quick apply

Taleo

Senior Data Science & AI Expert – AI Governance

Permanent contract

Brussels, Belgium

Hybrid

Skills

PythonMySQLGenerative AIAI Governance

14 hours ago

Quick apply

Taleo

Senior Data Science & AI Expert – AI Governance

Freelance

Brussels, Belgium

Hybrid

Skills

PythonMySQLGenerative AIAI Governance

14 hours ago

Quick apply

The best place to find your next move

© 2026. All Rights Reserved.

Talents

Find a job

Create a profile

Solutions and tools