豆包语音大模型后端工程师（模型推理） - Data语音
Core
Building and optimizing backend infrastructure for large-scale speech and music AIGC models, focusing on distributed inference, stability, and multi-modal audio technology.
Role type
Senior IC backend engineer (large model inference)
Builds
Scalable, high-availability distributed inference systems for speech understanding, generation, and multi-modal end-to-end audio models.
Domain
AI/ML, Large Language Models, Audio Processing, Cloud Infrastructure
Deliverable
production ML models
Required skills
Go, Python, Distributed Systems, K8s, MySQL, Redis, Kafka, Data Structures & Algorithms, Model Deployment
Preferred skills
Large model project experience, AI engineering/ops experience, Speech algorithm knowledge, Mainstream AI framework experience
Responsibilities
Engineering optimization and application of latest speech understanding/generation technologies, Architecting and optimizing distributed inference for scalability and resource efficiency, Managing service stability, concurrency optimization, and multi-region deployment, Supporting business products (Doubao, CapCut, TikTok) to enhance voice interaction and generation experiences.
