Upgrade to Pro — share decks privately, control downloads, hide ads and more …

LLMOps Operationalizing Large Language Models f...

Avatar for Raj Raj
March 28, 2025
Technology
98
0

LLMOps Operationalizing Large Language Models for the Real World

LLMOps Operationalizing Large Language Models for the Real World

Avatar for Raj

Raj

March 28, 2025

More Decks by Raj

See All by Raj
AI ENGINEER WORLD'S FAIR 2026 - We Cut 94% of Our AI Coding Tokens With a Local Code Index
Avatar for Raj rajkumarsakthi
0
23
A Software Engineer’s Guide to Raising Future-Ready Kids
Avatar for Raj rajkumarsakthi
0
180
Power of Minimalism in DevOps
Avatar for Raj rajkumarsakthi
0
150
Minimalism in DevOps 2023
Avatar for Raj rajkumarsakthi
0
190
Are You a Modern Software Engineer?
Avatar for Raj rajkumarsakthi
0
67
Minimalism in DevOps
Avatar for Raj rajkumarsakthi
0
95
Are You are a Modern DevOps Engineer?🤔
Avatar for Raj rajkumarsakthi
0
80
PHP Vegas : Modern Software Developer Best Practices 2020
Avatar for Raj rajkumarsakthi
2
110
PHP & Coding : Modern Software Developer
Avatar for Raj rajkumarsakthi
0
210

Other Decks in Technology

See All in Technology
制約理論（ToC）入門　2026版
Avatar for Recruit recruitengineers
PRO
3
360
研究開発部の紹介 / Sansan R&D Profile
Avatar for Sansan, Inc. sansan33
PRO
4
24k
ブラウザ研修 2026
Avatar for Recruit recruitengineers
PRO
3
450
『三匹の子ぶた』から学ぶネットワークセキュリティの昔と今 / Network Security: Then and Now Through the Lens of The Three Little Pigs
Avatar for NTT docomo Business nttcom
1
1.7k
【Google Cloud Next Tokyo'26】Gemini Enterprise と Oracle AI Database で実現する、 業務データ活用を実現する AI エージェント実装
Avatar for KoheiOgawa shisyu_gaku
0
210
組織にどうSREを根付かせるか？〜IVRyの場合〜
Avatar for abnoumaru abnoumaru
0
320
【CEDEC2026】専門性の高いデフォルメチームが挑んだ人材育成戦略 〜Cygames Academiaの企画から実施まで〜
Avatar for Cygames, Inc. cygames
PRO
0
250
AI駆動開発は個人技からチーム戦へ：組織でAIを使いこなすための実践設計
Avatar for Atsushi Nakatsugawa moongift
PRO
0
440
ボトムアップ文化が強い組織で セキュリティをどう根付かせていくかの現在進行形の話 / Making Security Stick in a Bottom-Up Organization
Avatar for Takashi Yamaguchi yamaguchitk333
0
120
[MIRU26] Open-Vocabulary Intention-Guided Object Detection in Diverse Scenes
Avatar for Semantic Machine Intelligence Lab., Keio Univ. keio_smilab
PRO
0
140
Retriever と Reranker、結局どうする？
Avatar for hkazuakey kazuaki
2
660
AI時代の強いチームの作り方
Avatar for yuukiyo yuukiyo
23
15k

Featured

See All Featured
Speed Design
Avatar for Sergey Chernyshev sergeychernyshev
33
2k
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
Avatar for Tech SEO Connect techseoconnect
PRO
0
570
The Language of Interfaces
Avatar for Des Traynor destraynor
162
27k
Neural Spatial Audio Processing for Sound Field Analysis and Control
Avatar for NII S. Koyama's Lab skoyamalab
0
390
Why Our Code Smells
Avatar for Brandon Keepers bkeepers
PRO
340
58k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
Avatar for Dan Newman danielanewman
230
23k
Technical Leadership for Architectural Decision Making
Avatar for Kenny Baas-Schwegler baasie
3
460
Dealing with People You Can't Stand - Big Design 2015
Avatar for Cassini Nazir cassininazir
367
27k
Intergalactic Javascript Robots from Outer Space
Avatar for Vicent Martí tanoku
273
27k
The innovator’s Mindset - 
Leading Through an Era of Exponential Change - McGill University 2025
Avatar for Jean-Marc De Jonghe jdejongh
PRO
1
230
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
Avatar for Marc Duiker marcduiker
35
2.5k
Reflections from 52 weeks, 52 projects
Avatar for Jefferson Lam jeffersonlam
356
21k

Transcript

  1. LLMOps Operationalizing Large Language Models for the Real World

  2. Hello! I’m Raj 😊 I ❤ to design & develop

    modern software

  3. About me Rajkumar Sakthivel (Raj) Senior Pro Dev @ Tesco

    Technology Founder @ tessellit_uk @rajkumarsakthi

  4. LLMOps Operationalizing Large Language Models for the Real World

  5. AI Disaster

  6. None
  7. None
  8. None
  9. None
  10. None
  11. None

  12. Cost

  13. None

  14. Real-World Challenges

  15. Hallucinations & Safety

  16. Cost Management

  17. Model Drift

  18. Security

  19. Best Practices

  20. RAG Workflow Rule 1: Start with RAG & Fine tune

    later

  21. Prompt Versioning: Rule 2: Treat prompts like code diff tool

    showing how changing ‘Summarize’ to ‘TLDR’ boosted accuracy

  22. GPU Optimization: Rule 3: Right-size GPUs Use A100s for training,

    T4s for inference
  23. None

  24. LLMOps bridges the prototype-to-production gap. Start small, monitor obsessively, and

    never trust an LLM alone with customers.

  25. Any Questions? 😊