多媒体算法工程师(AI Infra)-视频与边缘
Core
Develop and optimize training and inference algorithms for audio/video generation and multimodal large models to enable custom applications in scenarios like video style transfer and intelligent voice interaction.
Role type
Senior IC machine-learning engineer (multimodal AI & inference optimization)
Builds
Production-ready audio/video generation and multimodal large models
Domain
Multimedia, Generative AI, Edge Computing
Deliverable
production ML models
Required skills
Python, PyTorch, FSDP, DeepSpeed, Megatron, CUDA, AscendC, Triton, TileLang, FlashAttention, TensorRT-LLM, SGLang, vLLM, model quantization, parallel computing, operator optimization
Preferred skills
Heterogeneous computing, model architecture adaptation, multi-threaded development
Responsibilities
Track and apply frontier technologies in audio/video generation and multimodal models; Optimize training frameworks and strategies to maximize hardware utilization; Optimize inference algorithms for efficiency and speed; Engineer model deployment from lab to production environments.
Seniority
Senior, hands-on IC