Sr. Software Engineer - Inference Engine (Platform Software)
Seoul
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 3+ yearsEducation: bachelorsSkills: ["Problem-solving","Data analysis","Communication","Collaboration"]Develop and optimize a high-performance inference engine for large and multimodal LLMs running on FuriosaAI NPUs. Research and implement state-of-the-art inference optimizations (speculative decoding, KV-cache management, tensor/model parallelism, memory-efficient execution, and scheduling) to improve throughput, latency, and memory efficiency. Collaborate with the Compiler and hardware teams on distributed, scalable inference features like PD/EPD disaggregation and hierarchical KV-cache storage.
Loading
Loading job details...
Preparing the role view and application actions.

