AI Engineering for Decision makers
Foundations of AI Engineering and Generative AI for those leading AI transformation
📘 Overview
A technical deep dive into turning static LLMs into dynamic agents that can use tools, search data, and reason. This workshop helps participants understand:
AI Engineering: LLMs explained in clear, business-friendly terms.
LLM Applications: Using RAG and semantic search as a primary case study.
The Evolution of Transformers: From the 2017 breakthrough to the present.
LLM Optimization: The infrastructure needed to run models at scale.
Agentic Shift: Techniques that transformed simple chatbots into autonomous agents.
Key takeaway
A workshop designed to provide conceptual clarity for leaders and working code for engineers.
What you’ll learn
Embeddings: How the geometry of text data captures latent meaning.
Transformers: The engine behind foundational models.
Vector Databases: Storing the mathematical essence of data to enable semantic search.
RAG Evolution: Moving beyond simple vector search to Agentic RAG and Parent-Document Retrieval.
Reasoning Models: How models like DeepSeek-R1 and OpenAI’s o1 use Chain of Thought (CoT).
Tool Calling: How models learn to interact with external systems, APIs, and datastores.
Agents: Combining LLMs with tool calling and persistent memory.
LLM Training: An overview of how models are trained, fine-tuned, and aligned (RLHF).
Target audience
This session is for Decision Makers and Engineers looking to make informed choices in real-world AI projects. We will cover:
Local LLMs vs. Cloud-based APIs.
Fine-tuning vs. RAG.
Navigating the Vector Database landscape.
Reasoning vs. Non-reasoning models.
Build vs. Buy: Renting GPUs vs. On-premises inference.
Balancing Latency vs. Throughput.
✅ Prerequisites
The session will be most valuable if you have a baseline understanding of:
LLM Basics: Familiarity with tokens, context windows, and the difference between training and inference.
Search Intuition: A basic grasp of keyword search (exact matches) vs. semantic search (intent-based).
Technical Setup: A laptop with an IDE and Python installed, and/or familiarity with Google Colab.
API Access: An API key for an LLM provider (OpenAI, Anthropic, or Gemini) to test function calling.
Optional: Virtual environment setup with pip installation of necessary libraries like openai, transformers etc.
About the instructor
Arvind Devaraj (https://www.linkedin.com/in/arvinddevaraj/) is a Data Scientist with 15 years of experience across NVIDIA, Reliance Jio, and Juspay. Currently focused on the frontier of Generative AI, he architects high-performance RAG pipelines, optimizes LLM training and on-premises deployment. An IISc Bangalore Master’s graduate (AIR 7), Arvind bridges the gap between deep Transformer theory and practical, scalable implementation.
How to attend this workshop
This workshop is open for The Fifth Elephant annual members.
This workshop is open to 30 participants. Seats will be available on first-come-first-serve basis. 🎟️
Contact information ☎️
For inquiries about the workshop, contact +91-7676332020 or write to info@hasgeek.com