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...

Continues in

Multi-Agent Systems โ€” open the evidence trace โ†’

Continue reading

Read the original at infoq.com โ†’Open in live feedRead that dayโ€™s brief

Earlier in this thread 4 items