# 混元大模型音频理解算法工程师（北京）

External opening: you cannot apply through AI Native Match; apply on the official site.

Apply through the official channel. The full external receipt stays in your workspace. When signed in, three minimal event types explicitly recorded through the CLI are reported by default: selection, self-reported application and channel observation. Browsing or saving a role does not report an event; external applications do not appear under My applications.

- Company: 腾讯 (Listed company)
- Locations: Unknown
- Role: Algorithm
- Apply on the official site: https://careers.tencent.com/jobdesc.html?postId=1990262114463404032

## Role description from source

1.负责语音/音频大模型研发，包括音频理解（ASR/音频caption）、音视频理解等模型研发；
2.负责预训练、后训练、强化学习（文本和音频强化）相关的数据、算法、评测工作；
3.负责音频理解/ASR模型开源以及产品落地（比如产品全链路端到端优化、音频理解在噪音/口音/远场/音效音乐场景的优化）。
职位要求
1.有语音识别、音频理解、音乐理解等相关经验者优先；
2.有音视频多模态、大语言模型（预训练、微调、强化学习）等相关经验者优先；
3.优秀的代码能力、数据结构和算法功底，熟练掌握Python，熟悉Pytorch/Megatron/FSDP等模型训练框架、熟悉SLIME/VERL等RL框架优先；
4.有ACM/ICPC、NOI/IOI、Top Coder、Kaggle等比赛获奖者优先；
5.在相关顶级会议或期刊（如NeurIPS/ICLR/ICML/ACL/CVPR/ICASSP/INTERSPEECH等）有论文发表者优先；
6.良好的英语文献阅读能力，强烈的进取心/求知欲/团队合作精神，以及优秀的问题解决能力，热衷于追求技术创新。
工作年限（官方顶部字段）
三年以上工作经验

---
opening_id: a1c336b2-88f6-4fdc-9ff1-da535d3b1950

`anm openings save --id a1c336b2-88f6-4fdc-9ff1-da535d3b1950`