RAG / LLM Engineering Mentoring & Debugging with Sai Saran Dammavalam

Building a RAG application and stuck on architecture, retrieval quality, hallucinations, APIs or implementation?

Bring your problem to this session and we will work through it together.

We can cover areas such as:

• RAG architecture
• Chunking and document ingestion
• Embeddings and vector search
• Retrieval and reranking
• Prompt/context design
• Hallucination debugging
• FastAPI AI backends
• LLM application architecture
• Evaluation approaches
• Production-readiness considerations
• Project architecture and code-level problems

This is a practical technical session rather than a generic introduction to GenAI.

Before the session: Please share a short description of your problem and, where applicable, your architecture, GitHub repository or relevant code snippets. Do not share confidential company information, credentials or proprietary data.

You'll leave with: A clearer diagnosis of the problem and concrete next steps to implement.