Glean Logomark Blue
Product
WORK AI PLATFORM
Platform Overview
Platform Overview BG
Glean Assistant
Your personal AI assistant
All KnowledgeData AnalysisPrompt LibraryDeep ResearchCompanion
Glean Agents
Build and manage AI agents
Agent BuilderAgent OrchestrationAgent LibraryAgentic Reasoning Engine
Glean Search
The foundation of enterprise AI
Hybrid SearchKnowledge GraphCustom Language Models
Connectors
Connect to all company data
Model Hub
Get access to the latest models
APIs
Build generative AI experiences
Glean Protect
Safely scale AI at work
Security
Secure by design from day one
System of Context
Context powers productivity
GLEAN WHERE YOU WORK
Glean in SlackGlean in Microsoft TeamsGlean in ZoomGlean in Service CloudGlean in ServiceNowGlean in ZendeskGlean in GitHubBrowser Extension
Sign in
Customers
Solutions
INDUSTRIES
RetailFinancial Services
Sign in
Webinar
AI-powered engineering
Glean and Linkedin
Watch webinar
AI powered engineering
Resources
Sign in
State of AI Report Thumbnail
Read the whitepaper
About
Sign in
Get a demo
Get a demo

Veraj Paruthi

Engineering
, Glean

About

Veraj Paruthi

Veraj Paruthi is a Software Engineer at Glean. They have been with Glean since 2022 and play a key role in the company’s engineering team. Veraj holds a Bachelor's degree in Computer Engineering from the University of Waterloo and has previously worked with several organizations, including Tophatter and the Royal Canadian Air Force.

Connect with

Veraj Paruthi

Recent posts from

Veraj Paruthi

How KV caches impact time to first token for LLMs
July 23, 2024

How KV caches impact time to first token for LLMs

For part two of our series on LLM latency, we examined how KV caching impacts time to first token latency and throughput efficiency for calls.

Veraj Paruthi

Veraj Paruthi

Engineering

Enterprise Search + GenAI 101
Glean + Product
Industry Insights
How input token count impacts the latency of AI chat tools
July 2, 2024

How input token count impacts the latency of AI chat tools

Ever wonder what the impact of input token count is on the responsiveness of AI chat tools? We did—after some testing, here’s what we discovered regarding the correlation between input counts and time to first token.

Veraj Paruthi

Veraj Paruthi

Engineering

Glean + Product
Enterprise Search + GenAI 101