Story
infoq_ai_ml ยท Nov 17, 2026 ยท news
Source brief
Presentation: Scaling LLM-Based Ranking Systems for Latency-Critical Search & Recommendation Workloads
infoq.comNov 17, 2026
original source linked
In brief
Sundara Raman Ramachandran shares how LinkedIn productionizes LLM ranking under strict P99 latency SLAs. He discusses distilling a 7B model down to 400M parameters, compressing job contexts into single-token embedding...
