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

LLMOps Operationalizing Large Language Models f...

Sponsored · Ship Features Fearlessly Turn features on and off without deploys. Used by thousands of Ruby developers. →
Avatar for Raj Raj
March 28, 2025
Technology
0
73

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
Tweet

More Decks by Raj

See All by Raj
A Software Engineer’s Guide to Raising Future-Ready Kids
Avatar for Raj rajkumarsakthi
0
150
Power of Minimalism in DevOps
Avatar for Raj rajkumarsakthi
0
130
Minimalism in DevOps 2023
Avatar for Raj rajkumarsakthi
0
170
Are You a Modern Software Engineer?
Avatar for Raj rajkumarsakthi
0
45
Minimalism in DevOps
Avatar for Raj rajkumarsakthi
0
78
Are You are a Modern DevOps Engineer?🤔
Avatar for Raj rajkumarsakthi
0
60
PHP Vegas : Modern Software Developer Best Practices 2020
Avatar for Raj rajkumarsakthi
2
94
PHP & Coding : Modern Software Developer
Avatar for Raj rajkumarsakthi
0
180
Modern Software Developer Best Practices 2020
Avatar for Raj rajkumarsakthi
0
100

Other Decks in Technology

See All in Technology
AWSをCLIで理解したい！ / I want to understand AWS using the CLI
Avatar for める mel_27
2
200
バクラクのSREにおけるAgentic AIへの挑戦/Our Journey with Agentic AI
Avatar for SadayoshiTada taddy_919
2
1.1k
Exadata Database Service on Dedicated Infrastructure(ExaDB-D) UI スクリーン・キャプチャ集
Avatar for oracle4engineer oracle4engineer
PRO
8
7.1k
ビズリーチにおける検索・推薦の取り組み / DEIM2026
Avatar for Visional Engineering ＆ Design visional_engineering_and_design
1
120
「ヒットする」＋「近い」を同時にかなえるスマートサジェストの作り方.pdf
Avatar for なかしょ nakasho
0
150
EMからICへ、二周目人材としてAI全振りのプロダクト開発で見つけた武器
Avatar for Yuji Yamaguchi yug1224
5
480
作りっぱなしで終わらせない！ 価値を出し続ける AI エージェントのための「信頼性」設計 / Designing Reliability for AI Agents that Deliver Continuous Value
Avatar for Kento Kimura aoto
PRO
2
220
わたしがセキュアにAWSを使えるわけないじゃん、ムリムリ！(※ムリじゃなかった!?)
Avatar for cm-usuda-keisuke cmusudakeisuke
1
430
JAWSDAYS2026_A-6_現場SEが語る 回せるセキュリティ運用～設計で可視化、AIで加速する「楽に回る」運用設計のコツ～
Avatar for s-hata shoki_hata
0
2.9k
ブラックボックス観測に基づくAI支援のプロトコルのリバースエンジニアリングと再現 ~AIを用いたリバースエンジニアリング~ @ SECCON 14 電脳会議 / Reverse Engineering and Reproduction of an AI-Assisted Protocol Based on Black-Box Observation @ SECCON 14 DENNO-KAIGI
Avatar for chibiegg chibiegg
0
160
ヘルシーSRE
Avatar for Hiroki Takatsuka tk3fftk
2
250
管理者向けGitHub Enterpriseの運用Tips紹介: 人にもAIにも優しいプラットフォームづくり
Avatar for yuriemori yuriemori
0
170

Featured

See All Featured
KATA
Avatar for Megan Lloyd mclloyd
PRO
35
15k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
Avatar for Vitaly Friedman smashingmag
254
22k
Java REST API Framework Comparison - PWX 2021
Avatar for Matt Raible mraible
34
9.2k
Writing Fast Ruby
Avatar for Erik Berlin sferik
630
63k
[RailsConf 2023] Rails as a piece of cake
Avatar for Vladimir Dementyev palkan
59
6.4k
The Cost Of JavaScript in 2023
Avatar for Addy Osmani addyosmani
55
9.8k
Intergalactic Javascript Robots from Outer Space
Avatar for Vicent Martí tanoku
273
27k
Optimizing for Happiness
Avatar for Tom Preston-Werner mojombo
378
71k
Git: the NoSQL Database
Avatar for Brandon Keepers bkeepers
PRO
432
66k
Neural Spatial Audio Processing for Sound Field Analysis and Control
Avatar for NII S. Koyama's Lab skoyamalab
0
200
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
57
14k
JavaScript: Past, Present, and Future - NDC Porto 2020
Avatar for David Neal reverentgeek
52
5.9k

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? 😊