微信小程序-大模型算法工程师-Coding方向
Tencent Technology (Shenzhen) Co., Ltd.
广州Posted Aug 11, 2026
Overview
- Added in 30 days
- 501
- At this company, still open
Skills named in this posting
- Python
1.负责小程序代码大模型后训练工作,包括高质量训练数据合成与价值分析、SFT /RLVR 等训练方案设计落地,以及训练效果评估;
2.建设代码任务验证与奖励信号体系,综合运用多种验证策略,持续建模和校准奖励信号,为 RLVR 训练提供稳定、细粒度、可解释的反馈;
3.跟踪大模型后训练前沿技术,探索强化学习算法优化、奖励建模与 Agentic Coding 等方向,并推动在业务场景中落地。
1.计算机、数学等相关专业本科及以上学历,熟练使用 Python,具备良好的工程能力;
2.扎实的计算机与深度学习基础,深入理解 Transformer 架构及主流大模型训练框架;
3.具备大模型后训练项目经验,熟悉 SFT 与 RLVR 训练流程,理解奖励信号设计、强化学习算法调优与训练稳定性问题;
4.具备较强的数据处理与实验分析能力,能进行训练数据合成、清洗、价值评估与 badcase 归因,有大规模代码语料处理经验者优先;
5.具备快速学习与独立解决问题的能力,有团队合作精神,对探索前沿技术有持续热情。
Apply on the employer's site
Original posting: careers.tencent.com
RISC-V ecosystem
Tencent Technology (Shenzhen) Co., Ltd. in the RISC-V ecosystem
RISC-V International: Premier TSC
Tencent Holdings Ltd. is a Chinese multinational technology and entertainment conglomerate and holding company headquartered in Shenzhen.
- Tencent joined RISC-V International as China pushed for open-instruction-set alternatives (widely reported)
- Its TencentOS Tiny IoT operating system is used on RISC-V MCUs, e.g. tutorials pairing TencentOS Tiny with the GD32V RISC-V MCU
- Also participates in Chinese RISC-V community events such as the RISC-V Forum in Shenzhen
Same employer
More roles at Tencent Technology (Shenzhen) Co., Ltd.
- 深圳Oct 29, 2026
Associate Solution Architect, MPaaS 108179
Tencent Technology (Shenzhen) Co., Ltd.
伦敦Oct 29, 2026Security Operations Engineer
Tencent Technology (Shenzhen) Co., Ltd.
利雅得Oct 29, 2026《王者荣耀》内容创意策划(AI方向)-新星引力计划
Tencent Technology (Shenzhen) Co., Ltd.
深圳Oct 28, 2026《怪物猎人:旅人》-特效设计师
Tencent Technology (Shenzhen) Co., Ltd.
深圳Oct 28, 2026微信小店-产品运营-平台客服方向
Tencent Technology (Shenzhen) Co., Ltd.
广州Oct 28, 2026