Research Engineer / Scientist - Storage for LLM

Build and maintain a high-performance KV cache layer for large language model (LLM) inference, improving latency, throughput, and cost efficiency. Design distributed storage and caching across GPUs/nodes, optimize eviction and low-latency access for long-context inputs, and integrate cache reuse into token streaming, batched decoding, and model parallelism. Develop cache consistency protocols and evaluate/extend open-source GPU-aware KV caching solutions.