腾讯游戏-大模型训练框架研发工程师/专家
Core
Build and optimize large-scale pre-training frameworks for multimodal understanding and video generation models, focusing on long-context training and distributed efficiency.
Role type
Senior IC machine-learning engineer (large-scale training frameworks)
Builds
Production ML models (multimodal, video generation, LLMs)
Domain
AI / Large Language Models / Distributed Systems
Deliverable
production ML models
Required skills
Deep learning frameworks (PyTorch, JAX, TensorFlow), Large-scale distributed training, LLM/DiT training workflows, CUDA optimization, Parameter/Pipeline parallelism
Preferred skills
Megatron, DeepSpeed, FSDP, Mixed precision training, Sparse training
Technologies
PyTorch, JAX, TensorFlow, CUDA, Megatron, DeepSpeed, FSDP
Responsibilities
Optimize distributed training framework efficiency and compute utilization; Support long-context training scenarios; Collaborate with algorithm and data teams to automate end-to-end training deployment.
Seniority
Senior, hands-on IC