66 - Scaling LLMOps | Avi Lumelsky (Oligo)
From LangTalks by Lee Twito, Gal Peretz
April 12, 2026 · 29 min · Season 1 · Episode 66
About this episode
The episode discusses real-world use cases of LLMOps, focusing on vulnerability detection and malicious command detection, along with optimization strategies.
Two real-world use cases are covered: CVE Enrichment for open-source vulnerability detection and real-time Malicious Command Detection, along with practical tips on cost optimization, prompt caching, and open-source vs. commercial model trade-offs.
People in this episode
Hosts: Lee Twito, Gal Peretz
Guest: Avi Lumelsky
Topics covered
- LLMOps
- CVE Enrichment
- vulnerability detection
- Malicious Command Detection
- cost optimization
- prompt caching
- model trade-offs
Keywords
- LLMOps
- CVE Enrichment
- vulnerability detection
- Malicious Command Detection
- cost optimization
- prompt caching
- open-source models
- commercial models
Mentioned in this episode
Organizations: Oligo
More episodes of LangTalks
- 69 - Marketing for Agents | Nevo David (Postiz) · June 8, 2026 · 35 min
- 68 - AI-SDLC | Yonatan Maor (Clears.ai) · May 24, 2026 · 23 min
- 67 - FinOps for AI | Yizhar Gilboa (Finout) · April 27, 2026 · 27 min
- 65 - AI SRE | Asaf Savich (Komodor) · March 21, 2026 · 24 min
- 64 - AI coding metrics | Liad Elidan (Milestone) · March 8, 2026 · 28 min
- 63 - WAKE UP · February 23, 2026 · 29 min
Explore listener stats, chart rankings, contacts and more on the LangTalks podcast page.