Software Engineer — Distributed LLM Inference Systems
Shanghai
Workplace: OnsiteFull timeFunction: Software Engineering0Education: mastersSkills: ["Problem-solving","Performance optimization","Debugging","Collaboration","Communication"]Design, develop, and optimize distributed inference systems for large language models on Intel’s AI Frameworks team. You’ll implement distributed inference algorithms, optimize model execution and communication, and build components such as request schedulers, KV cache management, and communication layers. Profile workloads to address latency, throughput, scalability, and resource utilization, and contribute production-quality code, tests, and documentation to internal and open-source projects.
Loading
Loading job details...
Preparing the role view and application actions.

