Research Engineer, Artificial General Intelligence
职位介绍
We are seeking a hands-on Research Engineer to advance multimodal large-language foundational models (LLMs) at scale.
You will design and implement novel algorithms and modeling techniques for pre-training and post-training workflows.
Scale model training on hyper-large GPU clusters and AWS Trainium, while optimizing distributed training and parallelism.
Refine low-level training stack components, including CUDA kernels, communication collectives, and network I/O, to maximize efficiency.
Utilize and extend industry-leading frameworks (NeMo, Megatron Core, PyTorch, Jax, vLLM, TRT) and evaluate technical feasibility.
Deliver results independently in a self-organizing Agile environment while adapting to new scientific advances and collaborating with teammates.
You will design and implement novel algorithms and modeling techniques for pre-training and post-training workflows.
Scale model training on hyper-large GPU clusters and AWS Trainium, while optimizing distributed training and parallelism.
Refine low-level training stack components, including CUDA kernels, communication collectives, and network I/O, to maximize efficiency.
Utilize and extend industry-leading frameworks (NeMo, Megatron Core, PyTorch, Jax, vLLM, TRT) and evaluate technical feasibility.
Deliver results independently in a self-organizing Agile environment while adapting to new scientific advances and collaborating with teammates.
查看完整职位
工作职责、任职要求、技能与福利 — 免费创建账号即可查看。
或
已有账户？
登录您可能也感兴趣的职位
暂无高度相似的职位 — 以下是最新职位。