1,831,020open jobs
105,451companies
274,837added this week
Browse all
Location
In office (Beijing)
Seniority
Senior

Confirmed on the employer's own hiring board on Oct 18, 2026. First seen by Alion on Sep 6, 2026. JD.com scores A on the Alion truth index.

Overview
Company
Impact
Profile match
JD.com is a Chinese retailer and logistics operator founded in 1998 by Richard Liu, which moved online in 2004 and built its business on first-party inventory rather than a pure marketplace model. Unlike its peers it owns most of the goods it sells and runs its own nationwide warehouse and delivery network, which gives it tight control over authenticity and same-day or next-day fulfilment for hundreds of millions of customers. The group has expanded into logistics services for third parties, healthcare, industrial supply, cloud computing and consumer finance, and is listed in both New York and Hong Kong.

岗位职责 / Responsibilities

我们是金融科技事业群,作为京东科技旗下核心事业群之一,主要业务聚焦于金融领域与科技技术的融合创新。在过去10余年间,我们基于服务京东内外生态的经验与积淀,从京东供应链走向产业供应链,携手金融机构等合作伙伴,陆续推出了多款供应链金融、消费金融、支付科技、信用卡数字化运营、财富管理、数据科技等产品,为大中小型企业及广大个人用户提供丰富便捷的金融科技服务。我们形成了覆盖京东内场+生态、科技+金融、上游+下游、B端+C端的全产业链综合服务能力。欢迎加入我们,一起推进产业与金融的优化融合与价值创造。

1.负责京东金融核心场景(支付场景推荐、金融内容推荐、企业商户商品推荐、通用转化率预估等)的推荐算法建设,构建面向支付、内容、B 端交易的个性化推荐体系,并为各业务线提供通用的 CVR 预估能力;

2.核心指标优化:负责支付场景推荐、金融内容推荐、企业商户商品推荐等核心场景的算法优化,持续提升 CTR、CVR 及业务转化指标;

3.推荐链路深挖:深入优化推荐系统全链路,包括特征体系、多路召回、精排、重排及策略调优(优惠力度、推荐位序、额度分配等),利用深度学习技术解决冷启动、多样性与相关性平衡等难题;

4.转化率预估能力建设:构建可复用的通用 CVR 预估能力,支撑新业务场景低成本快速接入; 推动特征口径规范化与数据质量前置校验,规避特征穿越与样本偏差导致的重复回溯;

5.多目标与长效建模:构建多目标优化模型(MMoE、PLE 等),平衡点击、转化与业务收益,优化多场景流量分配机制;

6.前沿技术落地:跟踪生成式推荐、大模型(LLM)辅助推荐、图表示学习等前沿方向,并将其转化为实际业务生产力;

7.效果跟进与归因:定义评测指标,主导 A/B 实验与效果归因分析,用数据驱动迭代。

任职要求 / Requirements

1.专业背景:计算机、数学、数据挖掘或 AI 相关专业本科及以上学历;

2.行业深耕:推荐算法或相关领域(广告、搜索)从业经验,有大规模推荐系统实战经验,能独立解决数据冷启动、样本偏差、特征穿越等复杂问题;

3.技术背景:精通深度学习在推荐领域的应用(Wide&Deep、DeepFM、DIN/DIEN、Transformer 等系列模型),熟悉多目标优化(MMoE、PLE 等)与经典召回排序方法(协同过滤 / 向量召回 / LR / GBDT);

4.工程能力:精通 Python/Java/C++ 至少一种语言,熟悉分布式计算框架(Spark/Flink)及深度学习框架(TensorFlow/PyTorch),具备海量数据处理能力;

5.软素质:对数据敏感,理解"模型效果好 ≠ 业务收益好",能定义并跟踪北极星与护栏指标; 具备优秀的沟通能力与跨团队推动力;

6.符合京东价值观:客户为先、创新、拼搏、担当、感恩、诚信。

加分项

1、有金融 / 消费金融 / 支付场景推荐或用户增长经验(消费信贷、支付、企业金融等业务)。

2、有增长 / 营销算法经验:营销发券、优惠力度决策、转化率预测、用户分层建模。

3、熟悉线上推荐链路工程化(特征平台、在线推理、A/B 实验平台)的完整落地经验。

4、在生成式推荐、LLM + 推荐或多模态推荐领域有实际落地经验,或在 RecSys、KDD、SIGIR 等顶会发表过论文、在知名算法比赛中获奖。

Free account
Stop reading job ads. Get the ones that fit.
One free account turns this page into a shortlist built around your stack, your level and your pay.
Match on every job. Stack, seniority, pay and location, scored against your profile.
1,831,020 open roles. Read straight off company career pages, refreshed every day.
Unlimited applications. Every one you send is tracked in one place, on-site or on a company board.
3 tailored CVs a month. Rewritten for the exact job you are applying to. Included free.
Create a free account Continue with Google
Free forever. No card. Under a minute.

Your match

How well do you fit this role?
Two answers are enough for a real match. No account needed.
Check my fit
Answers stay in this browser until you create an account.

Recommended for you based on this role

AI/ML
Similar stack
Same company
Beijing
In office • Full-Time • Shanghai
C++
AI/ML
NLP
Apply
In office • Internship • Hangzhou
AI/ML
Model Context Protocol
A2A
Apply
In office • Full-Time • Beijing
C++
AI/ML
RLHF
Function Calling
Context Engineering
Agentic Workflows
Tool Use
Apply
In office • Internship • Shanghai
Python
Java
PHP
C++
Apply
In office • Full-Time • Shanghai
AI/ML
Function Calling
Tool Use
Apply
≈ $48k – $133k per year (Estimated) • In office • Full-Time • Beijing
Apply
≈ $30k – $87k per year (Estimated) • In office • Full-Time • 2+ years exp • Beijing
Apply
≈ $48k – $133k per year (Estimated) • In office • Full-Time • Beijing
Apply
≈ $30k – $87k per year (Estimated) • In office • Full-Time • 2+ years exp • Beijing
Apply
≈ $48k – $133k per year (Estimated) • In office • Full-Time • Beijing
Apply
See all jobs
This is one of many
1,831,020 more open roles from verified company boards, updated every day.