Research Intern (Inference Infrastructure) - 2027 Start (PhD)

Job description

About the Team The ByteDance DPU (Data Processing Unit) team builds foundational cloud and AI computing infrastructure for ByteDance and Volcano Engine. Our mission is to advance the architecture, development, and research of next-generation software-hardware co-design technologies across compute, networking, and storage for cloud and AI computing. Our technology stack spans - Cloud virtualization, hypervisors, and operating systems - High-performance networking, including DPDK and RDMA - High-speed interconnects, virtual switching, and network offload - Distributed storage and I/O acceleration - Orchestration and scheduling for AI/ML workloads We work at the intersection of systems research, distributed infrastructure, and hardware acceleration. Our technologies operate at cloud scale and help shape the next generation of cloud and AI computing platforms. We are looking for talented individuals to join us for an internship. PhD internships at Our Company provide students with the opportunity to actively contribute to our products and research, as well as to the organization's future plans and emerging technologies. Our dynamic internship experience blends hands-on learning, enriching community-building and professional development events, and collaboration with industry experts. Applications will be reviewed on a rolling basis, so we encourage you to apply early. Please clearly state your availability in your resume (Start date, End date). Responsibilities - Design and build large-scale, container-based cluster management and orchestration systems with extreme performance, scalability, and resilience. - Architect next-generation cloud-native GPU and AI accelerator infrastructure to deliver cost-efficient and secure ML platforms. - Collaborate across teams to deliver world-class inference solutions using vLLM, SGLang, TensorRT-LLM, and other LLM engines. - Stay current with the latest advances in open source (Kubernetes, Ray, etc.), AI/ML and LLM infrastructure, and systems research; integrate best practices into production systems. - Write high-quality, production-ready code that is maintainable, testable, and scalable. Minimum Qualifications - Currently pursuing a PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field. - Able to commit to working for 12 weeks during Summer 2027 - Strong understanding of large model inference, distributed and parallel systems, and/or high-performance networking systems. - Hands-on experience building cloud or ML infrastructure in areas such as resource management, scheduling, request routing, monitoring, or orchestration. - Solid knowledge of container and orchestration technologies (Docker, Kubernetes). - Proficiency in at least one major programming language (Go, Rust, Python, or C++). Preferred Qualifications - Experience contributing to or operating large-scale cluster management systems (e.g., Kubernetes, Ray). - Experience with workload scheduling, GPU orchestration, scaling, and isolation in production environments. - Hands-on experience with GPU programming (CUDA) or inference engines (vLLM, SGLang, TensorRT-LLM). - Familiarity with public cloud providers (AWS, Azure, GCP) and their ML platforms (SageMaker, Azure ML, Vertex AI). - Strong knowledge of ML systems (Ray, DeepSpeed, PyTorch) and distributed training/inference platforms. - Excellent communication skills and ability to collaborate across global, cross-functional teams. - Passion for system efficiency, performance optimization, and open-source innovation.