The Speech team at ByteDance is looking to empower content interaction and creation using speech & audio related technologies by focusing on cutting-edge R&D in speech & audio, music processing, natural language understanding, and multimodal deep learning. They aim to integrate these advanced technologies into various products to enhance user experience.
Requirements
- Experience in python/C++ and solid software engineering background.
- Proficient in data structure and algorithm design, and familiar with system performance tuning and Linux development environment;
- Experience with standard deep learning frameworks, e.g. Pytorch and Tensorflow.
- Understanding of basic deep learning algorithms.
- Experience in developing large scale AI application services, including model deployment and model serving, is preferred.
- Experience in one or more topics in model performance optimization, such as kernel fusion, KV cache optimization, quantization, etc., is preferred.
Responsibilities
- Responsible for the development of large-scale AI systems, solving technical difficulties such as high concurrency, high reliability, and high scalability of the system.
- Optimize deep learning models for lower latency, targeting backend server deployment.
- Work with researchers to land advanced technologies to ByteDance products.
- Build automation frameworks and tools to ensure high engineering quality and efficiency.
Other
- Currently pursuing a BS/MS in Software Development, Computer Science, Computer Engineering, or a related technical discipline
- Successful candidates must be able to commit to an onboarding date by end of year 2026.
- Please state your availability and graduation date clearly in your resume.
- Ability to work collaboratively in a fast paced, multi-functional environment.
