Join us | 诚聘英才

[fumiama]

We are the ChatTTS team 2noise, committed to integrating voice modality into the LLM system, reshaping the existing human-computer interaction mode.

At the end of May this year, we released ChatTTS on GitHub, which was well received and quickly secured seed round investment from top dollar VCs.

In order to ensure the continuous and rapid iteration of our model, we are looking for an experienced Senior Engineer / Technical Partner to join our team, focusing on the training of AR-based large voice models.

We hope you

1. Are proficient in traditional machine learning algorithms, able to analyze repeated patterns and statistical laws in data.
2. Can work with the existing team to build and improve a powerful audio preprocessing pipeline, and jointly build a data warehouse.
3. Can follow and independently reproduce papers in the field of small sample algorithms, identify shortcomings, and communicate and improve in a timely manner.
4. Bonus: Familiar with AR or diffusion-based audio generation models such as RALLE, AudioLDM.

At the same time, we hope you

1. Have good communication skills, can work in a team, and achieve goals.
2. Are able to learn continuously, have a certain degree of stress resistance, and can grow with the team in the early stage.

Contact Information

• career@2noise.com

---

我们是 ChatTTS 背后的团队2noise, 立志将语音模态融入 LLM 体系, 重塑现有人机交互模式.

今年5月底, 我们在 GitHub 发布了 ChatTTS, 广受好评, 并在短时间内获得头部美元 VC 的种子轮投资.

为了模型的持续快速迭代, 我们正在寻找一位经验丰富的 高级工程师 / 技术合伙人 加入我们的团队, 专注于AR-based语音大模型的训练.

我们希望你

1. 能熟练运用传统机器学习算法, 分析数据中重复的 pattern 和统计规律.
2. 与现有团队共同打造和改进强大的 audio 预处理 pipeline, 共同搭建数据仓库.
3. 能够 follow 并独立复现小样本算法领域的论文, 发现缺点并及时沟通和改进.
4. 加分项: 熟悉 RALLE, AudioLDM 等 AR or diffusion-based 音频生成模型.

同时, 我们希望你

1. 有良好的沟通能力, 能够团队协作, 完成目标.
2. 能够不断学习, 具备一定的抗压能力, 在初期能与团队共同成长.

联系方式

• career@2noise.com

Base

• 北京 (特殊情况另议)

薪资待遇

• 正式40k-80k*15
• 实习400-800/天
• 技术合伙人另议