AI全栈开发工程师 - 抖音音乐
Core
End-to-end R&D for AI music products, integrating large models and audio generation capabilities into C-end music creation/editing and B-end efficiency/copyright scenarios.
Role type
Senior Full-Stack AI Engineer (Audio/Music)
Builds
AI music creation tools, audio editing platforms, and model service infrastructure for music apps.
Domain
Music streaming and AI audio generation
Deliverable
production ML models
Required skills
Full-stack development, Go/Python/Java/C++/Node.js, LLM application development, RAG, AI Agent, Prompt Engineering, Audio processing, Distributed systems
Preferred skills
Audio signal processing, Music creation tools, High-concurrency optimization, Model training/inference optimization
Technologies
Large Language Models, Audio Diffusion Models, RAG, AI Agents, MCP, Vector Embeddings
Responsibilities
Develop end-to-end AI music products for creation and editing scenarios; Build core interactive experiences for audio playback, editing, and AI generation feedback; Optimize AI service chains, model scheduling, and Agent architecture; Explore and implement Multi-Agent, RAG, and controllable generation technologies.
