BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-cz-2025//speaker//XJU8CH
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-cz-2025-XRZYAR@pretalx.devconf.info
DTSTART;TZID=CET:20250612T153000
DTEND;TZID=CET:20250612T160500
DESCRIPTION:Deploying AI/ML models in production involves more than just tr
 aining—it's about building scalable\, secure\, and automated pipelines. 
 This talk focuses on how AIOps can enable production-grade deployment of M
 L workflows using cloud-native tools. We’ll walk through an end-to-end a
 rchitecture built on GitLab CI/CD\, Terraform\, GKE\, and FastAPI\, showca
 sing how to automate infrastructure\, containerize applications\, and moni
 tor deployed models.\n\nAs a use case\, we’ll demonstrate deploying a se
 lf-hosted LLM for intelligent Q&A over internal documents using RAG. The f
 ocus will be on infrastructure\, automation\, and best practices for takin
 g any AI workload—from concept to production.
DTSTAMP:20260611T171454Z
LOCATION:E104 (capacity 72)
SUMMARY:AIOps: Automating and Scaling ML and LLM Workloads in Production - 
 Niket  Ranjan
URL:https://pretalx.devconf.info/devconf-cz-2025/talk/XRZYAR/
END:VEVENT
END:VCALENDAR