Research Scientist Graduate （High-Performance Computing (Inference Optimization) - Vision AI Platform-Seattle)) - 2025 Start (PhD)

ByteDance • Seattle, WA

96d

About The Position

Founded in 2023, the ByteDance Doubao (Seed) Team, is dedicated to pioneering advanced AI foundation models. Our goal is to lead in cutting-edge research and drive technological and societal advancements. With a strong commitment to AI, our research areas span deep learning, reinforcement learning, Language, Vision, Audio, AI Infra and AI Safety. Our team has labs and research positions across China, Singapore, and the US. Leveraging substantial data and computing resources and through continued investment in these domains, we have developed a proprietary general-purpose model with multimodal capabilities. In the Chinese market, Doubao models power over 50 ByteDance apps and business lines, including Doubao, Coze, and Dreamina, and is available to external enterprise clients via Volcano Engine. Today, the Doubao app stands as the most widely used AIGC application in China.

Responsibilities

• Design and develop next-generation large model inference engines, optimizing GPU cluster performance for image/video generation and multimodal models to achieve industrial-grade low-latency & high-throughput deployment.
• Lead inference optimization including CUDA/Triton kernel development, TensorRT/TRT-LLM graph optimization, distributed inference strategies, quantization techniques, and PyTorch-based compilation (torch.compile).
• Build GPU inference acceleration stack with multi-GPU collaboration, PCIe optimization, and high-concurrency service architecture design.
• Collaborate with algorithm teams on performance bottleneck analysis, software-hardware co-design for vision model deployment, and AI infrastructure ecosystem development.

What This Job Offers

• Career Level: Entry Level
• Industry: Publishing Industries
• Number of Employees: 5,001-10,000 employees