Algorithms, data structures, system design, and computer science theory
Don't miss new videos — get them as they're added
Get new videos
If an AI agent is very slow, what can we do? 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 ~7 minutes with @aloo_explains. AI engineering program for software engineers: https://aiengg.dev 00:00 Agent with high latency 01:42 Sync vs Async tools 02:54 MCP tools 05:06 Tool composition 07:13 Bloopers
What is the Border Gateway Protocol? Cloudflare knows it too well. Article: https://blog.cloudflare.com/route-leak-incident-january-22-2026/ System Design Course: https://interviewready.io
In this live class, we will be going through the "Why Do Multi-Agent LLM Systems Fail?" research paper by Mert Cemri, Melissa Z. Pan and others, with Matei Zaharia and Ion Stoica. The paper studies 1,642 traces from seven multi-agent frameworks and names 14 ways these systems fail. We will also look at Anthropic's multi-agent research system, which beat a single Claude Opus 4 agent by 90.2% on its research eval, and used about 15 times the tokens of a chat. ---------------------------------------- Registrations for AI System Design Cohort 2026 have started. The cohort will start on 7th November 2026. Main topics: Week 1. Agentic System Design Week 2. Search and Retrieval Week 3. Evals and Agent Security Week 4. Agent Deployment and CI/CD Week 5. Observability and Scaling Week 6. Production Capstone Dates: 7th Nov to 13th Dec 2026 Time: Sat & Sun, 9 to 10:30 AM IST This cohort is for software engineers who want to build AI systems for production. You can register here: https://aiengg.dev/?utm_source=youtube&utm_medium=live&utm_campaign=paper-5 Cheers! Paper link: https://arxiv.org/abs/2503.13657 Anthropic's report: https://www.anthropic.com/engineering/multi-agent-research-system Github resources: https://github.com/InterviewReady/ai-engineering-resources AI Engineering Cohort: https://aiengg.dev/
If our AI chatbot is taking too long to respond, what can we do to reduce latency? 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 ~6 minutes. To crack more questions, subscribe to the channel! AI engineering program for software engineers: https://aiengg.dev 00:00 Optimize the AI Chatbot 00:36 Root Cause Analysis 02:23 Optimizing DB queries 04:19 Follow-up question 05:49 Bloopers Want your interview questions answered? Post them here: https://forms.gle/Bvo65mU4gUqCdwZQ8 #LLMs #AI #InterviewReady
If your RAG pipeline is inaccurate, what should you do? 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 7 minutes. To crack more questions, subscribe to the channel! AI engineering program for software engineers: https://aiengg.dev 00:00 How to improve a RAG pipeline? 00:30 Diagnosing retrieval problems 03:20 Where vector similarity falls short 05:56 Latency, cost, and accuracy trade-offs 06:45 Bloopers Want your interview questions answered? Post them here: https://forms.gle/Bvo65mU4gUqCdwZQ8 #LLMs #AI #InterviewReady
How Software Engineers Stay Relevant in the Age of AI. Moving toward a Forward Deployed Engineer or Solutions Architect role? In this conversation, Arvind and I talk about the fundamentals every engineer should learn, why taste and evaluation matter more than code speed, and how to build credibility by building in public. Chapters 00:00 Intro 00:26 How do we stay relevant as SDEs? 02:52 What managers want 04:59 Too much AI-generated code 07:11 10+ years of experience: is AI better than me? 10:10 Build in public to create a track record Links: Arvind on LinkedIn: https://www.linkedin.com/in/arvindna/ Arvind's academy: https://www.thegenacademy.com/ Gaurav's AI Engineering cohort: https://aiengg.dev #GenAI #LLMs #FDE
If you have a 1M Context Window, do you really need anything else? 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 7 minutes. To crack more questions, subscribe to the channel! AI engineering program for software engineers: https://aiengg.dev 00:00 Question - Improve the existing AI app 00:28 RAG Architecture Diagram 01:56 Online queries with reranker 04:41 Parsing PDF documents 06:50 Bloopers :p Want your interview questions answered? Post them here: https://forms.gle/Bvo65mU4gUqCdwZQ8 #LLMs #AI #InterviewReady
This is called Speculative Decoding. It speeds up LLMs by ~100%. References: OpenAI: https://openai.com/index/gpt-5-6-frontier-intelligence-efficiency/ Deepseek: https://arxiv.org/pdf/2607.05147 Gemini: https://research.google/blog/looking-back-at-speculative-decoding/ AI Engineering Website: https://aiengg.dev
Coding is solved.. again. But bugs are NOT solved. What does that even mean, let's find out? Thank you WorkOS for sponsoring. Try them out for here https://neetcode.fyi/workos For sponsorship & business inquiries [email protected] 🚀 https://neetcode.io/ - A better way to prepare for technical interviews Second Channel: https://www.youtube.com/@NeetCodeIO 🧑💼 LinkedIn: https://www.linkedin.com/in/navdeep-singh-3aaa14161/ 🐦 Twitter: https://twitter.com/neetcode1 #coding #leetcode #python
How do we choose between RAG pipelines and agentic pipelines? 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 11 minutes. To crack more questions, subscribe to the channel! AI engineering program for software engineers: https://aiengg.dev 00:00 Question - RAG vs Agents 00:35 Difference between RAG and Agents 01:45 What can RAG make tool calls 02:54 Agentic RAG 03:47 Bloopers :p Post your interview questions here: https://forms.gle/Bvo65mU4gUqCdwZQ8 #LLMs #AI #InterviewReady
How do we evaluate RAG pipelines with LLMs? 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 11 minutes. To crack more questions, subscribe to the channel! AI engineering program for software engineers: https://aiengg.dev 00:00 Question - Reliability with LLMs 01:00 Observability & Evals 02:50 What are evals? 06:41 Who does evals? 08:11 Answer relevancy, groundedness, tool sequence 10:39 Bloopers :p Post your interview questions here: https://forms.gle/Bvo65mU4gUqCdwZQ8 #LLMs #AI #InterviewReady
How do we cache prompts with LLMs? Interview with @aloo_explains. 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 6 minutes. To crack more questions, subscribe to the channel! AI engineering program for software engineers: https://aiengg.dev 00:00 Question - Prompt Caching with LLMs 00:39 Exact Query Caching 02:04 Semantic Caching 04:14 Tradeoffs 05:52 Blooper :p #LLMs #AI #InterviewReady
We finally get to examine a real agentic loop that mostly worked. It seems we are still reading code, even if not all of it. Thank you CodeRabbit for sponsoring. Try them out for free here https://neetcode.fyi/coderabbit Source: https://bun.com/blog/bun-in-rust#production For sponsorship & business inquiries [email protected] 🚀 https://neetcode.io/ - A better way to prepare for technical interviews Second Channel: https://www.youtube.com/@NeetCodeIO 🧑💼 LinkedIn: https://www.linkedin.com/in/navdeep-singh-3aaa14161/ 🐦 Twitter: https://twitter.com/neetcode1 #coding #leetcode #python
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 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
Original Blog: https://openai.com/index/harness-engineering/ AI Engineering Course: https://interviewready.io/course-page/ai-engineering
System Design Course at InterviewReady: https://interviewready.io
Claude Code's entire source code was leaked. And more interestingly, it was ported to Python to get around copyright laws. This has major implications for all programmers. Thank you Greptile for sponsoring. Try them out for free here https://www.greptile.com/go/neetcode Sources: https://www.cnbc.com/2026/03/31/anthropic-leak-claude-code-internal-source.html#:~:text=Anthropic%20was%20founded%20by%20a,fix%20bugs%20and%20automate%20tasks. https://github.com/instructkr/claw-code https://x.com/Fried_rice/status/2038894956459290963 https://x.com/wesbos/status/2038959754580492463 https://x.com/cmuratori/status/2039044968246038780 https://x.com/Butanium_/status/2039079715823128964 https://x.com/mal_shaik/status/2038919506224132178 🚀 https://neetcode.io/ - A better way to prepare for technical interviews Second Channel: https://www.youtube.com/@NeetCodeIO 🧑💼 LinkedIn: https://www.linkedin.com/in/navdeep-singh-3aaa14161/ 🐦 Twitter: https://twitter.com/neetcode1 #coding #leetcode #python
Thank you Posthog for sponsoring. Try them out for free here https://go.posthog.com/navi Thank you Greptile for sponsoring. Try them out for free here https://www.greptile.com/go/neetcode Check out OpenCode: https://opencode.ai/ You can find Dax here: https://x.com/thdxr The Full Episode: Spotify - https://open.spotify.com/episode/4pqIupaKYWHl8D4pZMr5hL?si=1-ESZEHzSTK8K_wJyxLFLw Apple - https://podcasts.apple.com/us/podcast/building-the-future-of-coding-opencode-with-dax-raad/id1867041268?i=1000752897650 0:00 - Intro 1:02 - The Origin of OpenCode 3:56 - Dax's developer workflow 6:54 - Is code no longer written by humans? 11:32 - Competition, Claude Code 19:04 - Positioning vs Product 23:49 - Will OpenAI acquire OpenCode? 28:02 - The Future of Coding, effort vs impact 37:16 - Code Quality 42:23 - Did AI take the fun out of programming? 45:56 - Will programming skills decay long term? 51:56 - Technical skills alone are useless 58:56 - Becoming an Elite Developer 1:04:03 - Hiring shortcuts, do credentials matter For sponsorship & business inquiries [email protected] 🚀 https://neetcode.io/ - A better way to prepare for technical interviews Second Channel: https://www.youtube.com/@NeetCodeIO 🧑💼 LinkedIn: https://www.linkedin.com/in/navdeep-singh-3aaa14161/ 🐦 Twitter: https://twitter.com/neetcode1 #coding #leetcode #python
Thank you Posthog for sponsoring. Try them out for free here https://go.posthog.com/navi Thank you Greptile for sponsoring. Try them out for free here https://www.greptile.com/go/neetcode Check out OpenCode: https://opencode.ai/ You can find Dax here: https://x.com/thdxr The Full Episode: Spotify - https://open.spotify.com/episode/4pqIupaKYWHl8D4pZMr5hL?si=1-ESZEHzSTK8K_wJyxLFLw Apple - https://podcasts.apple.com/us/podcast/building-the-future-of-coding-opencode-with-dax-raad/id1867041268?i=1000752897650 0:00 - Intro 1:02 - The Origin of OpenCode 3:56 - Dax's developer workflow 6:54 - Is code no longer written by humans? 11:32 - Competition, Claude Code 19:04 - Positioning vs Product 23:49 - Will OpenAI acquire OpenCode? 28:02 - The Future of Coding, effort vs impact 37:16 - Code Quality 42:23 - Did AI take the fun out of programming? 45:56 - Will programming skills decay long term? 51:56 - Technical skills alone are useless 58:56 - Becoming an Elite Developer 1:04:03 - Hiring shortcuts, do credentials matter For sponsorship & business inquiries [email protected] 🚀 https://neetcode.io/ - A better way to prepare for technical interviews Second Channel: https://www.youtube.com/@NeetCodeIO 🧑💼 LinkedIn: https://www.linkedin.com/in/navdeep-singh-3aaa14161/ 🐦 Twitter: https://twitter.com/neetcode1 #coding #leetcode #python