What goes in the context window of an LLM? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 5 minutes. To crack more questions, subscribe to the channel! AI engineering...
What goes in the context window of an LLM?
This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 5 minutes.
To crack more questions, subscribe to the channel!
AI engineering program for software engineers: https://aiengg.dev
00:00 Question - Context in LLMs
00:30 Basic Answer
02:46 Follow up
04:35 What is Memory?
07:22 Bloopers
#LLMs #AI #InterviewReady
What's better? LLMs or Agents? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 5 minutes. To crack more questions, subscribe to the channel! AI engineering program for...
What's better? LLMs or Agents?
This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 5 minutes.
To crack more questions, subscribe to the channel!
AI engineering program for software engineers: https://aiengg.dev
00:00 Question - LLMs vs. Agents
01:02 Basic Answer
02:16 Follow-up question
03:47 Context Management
05:08 Bloopers
#LLMs #AI #InterviewReady
Research Paper: https://arxiv.org/pdf/2607.05147 Title: DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation On 1st August 2026, we are launching the AI Engineering Cohort. It is a 10-week cohort, designed for software engineers who want...
Research Paper: https://arxiv.org/pdf/2607.05147
Title: DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
On 1st August 2026, we are launching the AI Engineering Cohort.
It is a 10-week cohort, designed for software engineers who want production-grade AI systems.
Register here: https://aiengg.dev/
Start Date: 1st August 2026
End Date: 4th October 2026
More details coming soon.
Cheers!
Thank you for joining the Lightning session on Mastering RAG-based systems for software engineers! Slides: https://docs.google.com/presentation/d/1DzwmTBOlyR-gbetAIJKyyaWiGxoHGMBIlWXYCQ2DeKg/edit?usp=sharing Code:...
Thank you for joining the Lightning session on Mastering RAG-based systems for software engineers!
Slides: https://docs.google.com/presentation/d/1DzwmTBOlyR-gbetAIJKyyaWiGxoHGMBIlWXYCQ2DeKg/edit?usp=sharing
Code: https://colab.research.google.com/drive/14U31jAf3tijMqV9bTKgLm6nfDkOq6hxF
00:00 What are Agents?
11:18 Code
21:40 MCP and Agents
25:40 MCP Code and ReAct
36:34 Questions
I hope you found the session useful. Let me know if you have any questions on WhatsApp at +91-9920533010 or email at contact@aiengg.dev.
If you are looking to transition to AI Engineering, check out our 10-week cohort here: https://aiengg.dev.
It's for software engineers who want to build production-grade AI applications.
Thank you for joining the Lightning session on Mastering RAG-based systems for software engineers! Slides: https://docs.google.com/presentation/d/1FZGeHal2nQrEIii-osLPuYOAEzcs-rYCPmWOA2zE6Vc/edit?usp=sharing Relevant resources:...
Thank you for joining the Lightning session on Mastering RAG-based systems for software engineers!
Slides: https://docs.google.com/presentation/d/1FZGeHal2nQrEIii-osLPuYOAEzcs-rYCPmWOA2zE6Vc/edit?usp=sharing
Relevant resources: https://www.notion.com/blog/two-years-of-vector-search-at-notion, https://www.uber.com/us/en/blog/enhanced-agentic-rag/
00:00 Intro to LLMs
07:00 What is Retrieval Augmented Generation
14:36 Indexing Documents
22:10 Document Reranking
27:08 Query Rewriting
34:44 Questions
I hope you found the session useful. Let me know if you have any questions on WhatsApp at +91-9920533010 or email at gkcs@aiengg.dev.
If you are looking to transition to AI Engineering, check out our 10-week cohort here: https://aiengg.dev.
It's for software engineers who want to build production-grade AI applications.
A hackathon for AI engineers in India. India's doctor-to-patient ratio is 1:11000. That's 11 times the ratio recommended by WHO. Through this hackathon, we are trying to scout talent who can build India's future AI capabilities. Join us using the link:...
A hackathon for AI engineers in India.
India's doctor-to-patient ratio is 1:11000. That's 11 times the ratio recommended by WHO.
Through this hackathon, we are trying to scout talent who can build India's future AI capabilities.
Join us using the link: https://luma.com/g4lf0iag
All the best :)
AI Engineering Program: https://aiengg.dev Should we fill in 1 million tokens into the context window of an LLM? This video explains the needle in a haystack problem. #AI #ContextWindow #LLM
AI Engineering Program: https://aiengg.dev
Should we fill in 1 million tokens into the context window of an LLM?
This video explains the needle in a haystack problem.
#AI #ContextWindow #LLM
On the 25th of March 2026, Discord had a global voice outage. This is a summary of its incident report. System Design Course at InterviewReady: https://interviewready.io/learn/system-design-course/building-an-ecommerce-app-1-to-1m/1-what-is-system-design?tab=chapters
On the 25th of March 2026, Discord had a global voice outage.
This is a summary of its incident report.
System Design Course at InterviewReady: https://interviewready.io/learn/system-design-course/building-an-ecommerce-app-1-to-1m/1-what-is-system-design?tab=chapters
Cohort Link: https://aiengg.dev 00:00 Introduction 00:48 1. Hallucinations in AI 04:28 2. Evals and Tool Calling 13:45 3. Taking AI to 100% Automation 20:33 4. What will happen in 5 years? 27:30 5. Is DSA Dead? 28:23 6. Is AGI Coming 29:55 7. Steps to Learn AI as an SDE 33:16...
Cohort Link: https://aiengg.dev
00:00 Introduction
00:48 1. Hallucinations in AI
04:28 2. Evals and Tool Calling
13:45 3. Taking AI to 100% Automation
20:33 4. What will happen in 5 years?
27:30 5. Is DSA Dead?
28:23 6. Is AGI Coming
29:55 7. Steps to Learn AI as an SDE
33:16 Thank you!
Core Theme: Problem Definition & Evaluation
The key to successful AI systems isn't the model—it's how well you define the problem and evaluate the solution. Problem definition accounts for 30% of success, evaluation 70%.
Main Points:
Problem Definition - Be explicit about constraints, tech stack, success metrics, and requirements. Don't give vague instructions to AI; frame the problem like you would for a human engineer.
Context Matters - Hallucinations don't just come from models; bad context you provide causes them. Scope context to what's actually needed for the problem.
Evaluation is Everything - Most engineers evaluate AI systems on output alone. The 5% winners evaluate on tool-calling sequences, decision-making logic, and whether the system followed proper patterns—not just whether the final answer looks right.
Example: Booking a Flight - A bad system just books the ticket (95% metric). A good system first gathers user data, identifies missing information (date, preferences, airline), asks clarifying questions, then books (5% thinking).
Subject Matter Experts Are Critical - Don't automate without verification. Sit with domain experts (nurses for healthcare, aerospace engineers for aviation) to validate prompts and instructions before deployment.
Don't Overcomplicate - Focus on fundamentals, not frameworks. Don't use LLM-as-judge as a cop-out; that's lazy when you should have ground truth and proper evaluation.
Bottom Line: Success comes from rigorous problem scoping, proper evaluation metrics, and subject matter expert involvement.
AI Engineering Cohort: https://aiengg.dev/ Github resources: https://github.com/InterviewReady/ai-engineering-resources On 6th June 2026, we are launching our first AI Engineering Cohort. A focused, intense 8-week program for software engineers who want real, production-grade...
AI Engineering Cohort: https://aiengg.dev/
Github resources: https://github.com/InterviewReady/ai-engineering-resources
On 6th June 2026, we are launching our first AI Engineering Cohort.
A focused, intense 8-week program for software engineers who want real, production-grade AI skills.
More details coming soon.
Cheers!
The title is descriptive enough! What's going on in the world of AI? Github resources: https://github.com/InterviewReady/ai-engineering-resources ---------------------------------------- 00:00 Checks 00:40 Who is Tanishq Singh? 02:45 1. What do you look for in an AI Engineer...
The title is descriptive enough! What's going on in the world of AI?
Github resources: https://github.com/InterviewReady/ai-engineering-resources
----------------------------------------
00:00 Checks
00:40 Who is Tanishq Singh?
02:45 1. What do you look for in an AI Engineer resume?
07:35 2. How do you test the claims of a candidate?
11:04 3. Should Software devs be worried about AI?
15:55 4. Is DSA required for an AI engineer interview?
18:46 5. Is getting a job harder now for freshers?
22:24 6. Is the token budget for companies making sense?
29:29 7. How do we stay updated in the world of AI?
33:03 8. CEO asks me to use AI and not write code?
34:37 9. AI cohort useful for a 10-year experienced engineer?
35:26 10. What AI topics should we know in 2026?
38:20 11. Can I move from SWE to AI or FDE?
40:00 12. AI Resources to use
40:30 13. What depth is needed to become an AI engineer?
42:55 14. AI Cohort Overview
AI Engineering Cohort: https://aiengg.dev/
On 6th June 2026, we are launching our first AI Engineering Cohort.
A focused, intense 8-week program for software engineers who want real, production-grade AI skills.
More details coming soon.
Cheers!
System Design Course at InterviewReady: https://interviewready.io/ AI Engineering Cohort: https://aiengg.dev You can follow me on Twitter: https://twitter.com/gkcs_ #LLMs #AI #Prompting
System Design Course at InterviewReady: https://interviewready.io/
AI Engineering Cohort: https://aiengg.dev
You can follow me on Twitter: https://twitter.com/gkcs_
#LLMs #AI #Prompting
If you are worried about AI taking over the world, please don't. AI CEOs would like you to believe that AGI is near. But there is no research basis for such an opinion. Stay skeptical, stay safe. Cheers :)
If you are worried about AI taking over the world, please don't.
AI CEOs would like you to believe that AGI is near. But there is no research basis for such an opinion.
Stay skeptical, stay safe.
Cheers :)
Uber uses a batch-matching algorithm, with DeepETA and RL for demand spikes. The video explains these points. References: https://www.uber.com/us/en/marketplace/matching/ https://www.uber.com/en-IN/blog/reinforcement-learning-for-modeling-marketplace-balance/...
Uber uses a batch-matching algorithm, with DeepETA and RL for demand spikes. The video explains these points.
References:
https://www.uber.com/us/en/marketplace/matching/
https://www.uber.com/en-IN/blog/reinforcement-learning-for-modeling-marketplace-balance/
https://www.uber.com/en-IN/blog/m3/
https://www.uber.com/en-IN/blog/deepeta-how-uber-predicts-arrival-times/
https://interviewready.io/learn/system-design-course/design-a-cab-aggregator-app-like-uber/requirements-of-a-cab-aggregator
#Uber #SystemDesign #InterviewReady