Senior Applied Scientist, Efficient LLM Inference & Model Optimization (opens in a new tab) London
- Location
- Greater London, England, United Kingdom
engineers canbuild on. Your research will span quantization, distillation, speculative decoding, KV-cache optimization, and model/runtime co-optimization, alongside inference engines and distributed inference architectures. You will investigate how these approaches interact, evaluate their trade-offs across model quality, latency, throughput, memory footprint, and cost per token … expert parallelism (WideEP). Study expert placement, load imbalance, and computation/communication trade-offs, and use the findings to guide model and system architecture choices. Develop rigorous evaluationscovering quality, latency, throughput, numerical stability, memory footprint, tail latency, and cost per token.Compare serving architectures under consistent workload conditions ...