San Francisco, California13 days ago
p style="min-height:1.5em">You'll write technical deep dives, build demos, create tutorials, contribute to docs and examples, host workshops, and help developers understand topics like KV cache, continuous batching, prefix caching, prefill and decode, quantization, GPU serving, latency versus throughput, and model-server tradeoffs across vLLM and adjacent systems. Ability to credibly explain systems concepts such as KV cache, PagedAttention, continuous batching, prefill / decode scheduling, prefix caching, speculative decoding, tensor parallelism, data parallelism, or latency versus throughput tradeoffs.