Read the abstract ➤ https://www.conf42.com/Site_Reliability_Engineering_SRE_2024_Chinmay_Naik_devops_mlops_scaling Other sessions at this event ➤ https://www.conf42.com/sre2024 Support our mission ➤ https://www.conf42.com/support Join Discord ➤ https://discord.gg/DnyHgrC7jC Chapters 0:00 intro 0:26 preamble 0:36 chinmay naik 1:12 agenda 1:38 what is mlops 2:30 mlops steps 4:05 simpelst mlops flow 6:11 production work ahead 6:37 case study - ekyc saas apis 7:01 ml model apis 8:20 architecture 9:54 ekyc saas apis - requirements 10:51 cloud agnostic architecture 13:45 why cloud agnostic? 14:34 scaling journey 16:19 eliminate single points of failure 18:36 capacity planning 20:35 cost optimization and autoscaling 24:27 production issue 1 - gpu utilization in nomad 27:41 production issue 2 - high latency issue 30:57 lessons 33:33 keep learning