Slide 1

Slide 1 text

LLMOps Operationalizing Large Language Models for the Real World

Slide 2

Slide 2 text

Hello! I’m Raj 😊 I ❤ to design & develop modern software

Slide 3

Slide 3 text

About me Rajkumar Sakthivel (Raj) Senior Pro Dev @ Tesco Technology Founder @ tessellit_uk @rajkumarsakthi

Slide 4

Slide 4 text

LLMOps Operationalizing Large Language Models for the Real World

Slide 5

Slide 5 text

AI Disaster

Slide 6

Slide 6 text

No content

Slide 7

Slide 7 text

No content

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

No content

Slide 12

Slide 12 text

Cost

Slide 13

Slide 13 text

No content

Slide 14

Slide 14 text

Real-World Challenges

Slide 15

Slide 15 text

Hallucinations & Safety

Slide 16

Slide 16 text

Cost Management

Slide 17

Slide 17 text

Model Drift

Slide 18

Slide 18 text

Security

Slide 19

Slide 19 text

Best Practices

Slide 20

Slide 20 text

RAG Workflow Rule 1: Start with RAG & Fine tune later

Slide 21

Slide 21 text

Prompt Versioning: Rule 2: Treat prompts like code diff tool showing how changing ‘Summarize’ to ‘TLDR’ boosted accuracy

Slide 22

Slide 22 text

GPU Optimization: Rule 3: Right-size GPUs Use A100s for training, T4s for inference

Slide 23

Slide 23 text

No content

Slide 24

Slide 24 text

LLMOps bridges the prototype-to-production gap. Start small, monitor obsessively, and never trust an LLM alone with customers.

Slide 25

Slide 25 text

Any Questions? 😊