Building with LLMs Workshop

A full-day hands-on workshop on building production-ready LLM applications.

What We Covered

Morning Session (10 AM - 1 PM)

• LLM Fundamentals & Architecture
• Prompt Engineering Best Practices
• Building RAG Pipelines with LangChain

Afternoon Session (2 PM - 5 PM)

• Fine-tuning with LoRA & QLoRA
• Deployment Strategies (vLLM, TGI)
• Cost Optimization & Monitoring

Instructors

• Rahul Sharma - ML Lead at Sarvam AI
• Priya Venkat - Former Google AI, now building in stealth

Takeaways

• Working RAG application template
• Fine-tuning notebook with Indian language data
• Cost calculator spreadsheet for LLM deployments

Feedback

"Best technical workshop I've attended. Left with actual working code." - Participant

"Finally understood when to use RAG vs fine-tuning." - Participant

Slides and code available to attendees in the community Discord.