The Fifth Elephant OSAI meet-up - Hyderabad edition
The Fifth Elephant
The Fifth Elephant

The Fifth Elephant OSAI meet-up - Hyderabad edition

Call for Proposals - make a submission; give visibility to your work

All submissions

Himanshu Aggarwal

Architecting for Speed: Building Real-time Search & Recommendation Systems with Modern AI Stacks

Submitted Sep 19, 2025

Type of session: 10 mins Lightning talk/demo

The demand for instant, relevant experiences in fast-paced industries necessitates a new generation of search and recommendation systems. This talk will deep dive into the modern AI stack powering these systems. We’ll explore multi-stage architectures, from two-tower models for scalable candidate generation using vector databases, to advanced pretrained and rerankers for pinpoint accuracy. The session will highlight how cutting-edge text, image, and multimodal embeddings, coupled with LLMs and VLMs, enable profound content understanding. You will learn practical strategies for designing, deploying, and optimizing these low-latency, high-throughput systems, ensuring rapid innovation and competitive advantage in 2025.

The expected audience is beginner to intermediate level.

Himanshu Aggarwal, a Machine Learning Engineer, specializes in designing and developing personalized recommender systems and advanced AI solutions. With a robust background spanning research labs, media streaming applications, and content delivery platforms, he brings a strong blend of research, engineering, and applied data science expertise. Passionate about search and recommendation systems, he focuses on leveraging AI to optimize content understanding and generation. Himanshu is dedicated to defining next-generation user experiences across various domains.

All submissions

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Register

Hosted by

The Fifth Elephant
The Fifth Elephant
Jump starting better data engineering and AI futures

Supported by

Community sponsor

Meta
Meta