What does "Learn what engineers at Google, Amazon and OpenAI know" mean?

It names the standard we hold the lessons to: depth beyond tutorials, with sources cited, results from code you can run, and evidence before opinion. "L12 knowledge" is shorthand for that depth, not a title or a promise, and levels differ from company to company. It does not say anyone from those companies teaches, reviews or endorses the courses. QFLOO is not affiliated with any of them, and it does not promise a job or a level.

Python and git for the hands-on courses. The labs run offline against stand-in models, so no API key is needed.

Where should I start?

New to AI: What Is AI?, then Working with LLMs. Shipping LLM features: Agent Reliability Engineering. Curious how models are served on GPUs: Inference and Serving Engineering. Every course has free lessons, so you can look before you choose.

How are the courses made?

Sources cited, results from running the lab code, a verified date shown. The author reads, runs and approves each lesson first.

Are all the courses finished?

A lesson is published only after the author has read it and run its code. Each card counts the lessons that are open today, and a course that is not open yet says Coming soon.

How do the plans work?

Lifetime is one payment with no renewal. Monthly, Quarterly and Annual are subscriptions billed every month, three months or year. The final price, with any taxes, shows before you pay. Checkout opens when payments are switched on.

Can I share my account?

No. One account is for one person. Do not share your login, sell access or let others use it. Only one device can be signed in at a time: signing in on a second device ends the first session. This is part of the Terms of Service.

What happens to my data?

We keep your email, name and learning progress to run your account, and nothing is sold. The Privacy Policy lists exactly what we store and why.

What if it is not for me?

The free lessons need no card, so you can find out before you pay anything.

No. All sales are final and there are no refunds, so try the free lessons first. Nothing renews automatically, so there is nothing to cancel. Billing mistakes by us or the payment provider are corrected. See the Refund policy at /refunds.

Learn what engineers at Google, Amazon, OpenAI, Anthropic, Microsoft, Meta, Apple and NVIDIA know.

L12 knowledge. Learn by building real projects.

Start free Explore the courses

Free lessons in every course. No card needed.Lifetime ₹10,000plans from ₹899 per month

Company names and logos belong to their owners. QFLOO is not affiliated with or endorsed by them.

Free 11 minBeginner

An agent is a model in a loop that calls tools

step 1: list_files({"directory": "src"}) -> 'a.py\nb.py\nc.py\nnotes.md'
step 2: read_file({"path": "src/a.py"}) -> '# TODO: handle empty input\nx = 1\n# TODO:'
step 3: read_file({"path": "src/b.py"}) -> 'y = 2\n'
step 4: read_file({"path": "src/c.py"}) -> '# TODO: remove this\n'
step 5: write_file({"path": "report.txt", "content": "3"}) -> 'wrote 1 characters to report.txt'
report.txt: 3

Checkpoint. Which message from the program caused the sixth call, and why does the loop stop after it?

Read this lesson free

Courses

Pick your path

Software and AI both move fast, and it is hard to know where to begin. Open any course to read its full outline and see exactly what you would understand by the end.

Advanced Python

13 modules · 53 lessons

Master Competitive Programming

17 modules · 82 lessons

Solve contest problems with a tested template, a stress-test habit and a toolkit of proven patterns, and run a practice routine built from your own weakness list.

You will learn to

Keep a contest toolkit and a practice routine built from your weak spots
Map constraints to algorithms: number theory, graphs, trees, flows, DP and strings
Solve problems the way an expert does, then stress test the solution

Open course: Master Competitive Programming

Practice and contests

Train Like a High-Rated Competitor5 lessons · 1 free
1. Diagnose weaknesses and build a practice routineFree
2. Run virtual contests and upsolve
3. Play ICPC, IOI and rated-round formats differently
4. Read a problem fast and budget the contest clock
5. Treat contest psychology as procedure

Toolkit

Keep a Contest Toolkit4 lessons · 1 free
Loading lessons. See the lessons in the course

Complexity

Map Constraints to Algorithms3 lessons · 1 free
Loading lessons. See the lessons in the course

Number theory

Number Theory7 lessons · 1 free
Loading lessons. See the lessons in the course

Polynomials and linear algebra

Polynomials and Linear Algebra3 lessons · 1 free
Loading lessons. See the lessons in the course

Combinatorics

Combinatorics4 lessons · 1 free
Loading lessons. See the lessons in the course

Data structures

Range Queries and Stacks4 lessons · 1 free
Loading lessons. See the lessons in the course

Advanced queries

Advanced Range Queries3 lessons · 1 free
Loading lessons. See the lessons in the course

Decomposition

Decomposition and Persistence5 lessons
Loading lessons. See the lessons in the course

Graphs

Shortest Paths and Connectivity8 lessons
Loading lessons. See the lessons in the course

Trees, flows, logic

Trees, Flows and Logic7 lessons
Loading lessons. See the lessons in the course

DP design

Dynamic Programming Design7 lessons
Loading lessons. See the lessons in the course

DP optimisation

Dynamic Programming Optimisation4 lessons
Loading lessons. See the lessons in the course

Strings

String Algorithms5 lessons
Loading lessons. See the lessons in the course

Geometry

Geometry4 lessons
Loading lessons. See the lessons in the course

Reasoning patterns

Reasoning Patterns6 lessons
Loading lessons. See the lessons in the course

Capstone

Capstone3 lessons
Loading lessons. See the lessons in the course
Project Assemble and test your personal library

Deep Dive into Databases

14 modules · 65 lessons

What Is AI? A Clear Introduction

5 modules · 26 lessons

Build Your First AI Application

4 modules · 24 lessons

Working with LLMs: Prompts, Context and Limits

5 modules · 28 lessons

AI Agents: What They Are and How to Build One

5 modules · 26 lessons

How AI Is Built: From Data to a Working Model

6 modules · 30 lessons

System Design for AI Products

9 modules · 40 lessons

ML Mathematics for AI Engineers

10 modules · 45 lessons

Compute, check and explain the mathematics inside a model (shapes, gradients, likelihoods, entropy and floating point error) well enough to debug a training run from the numbers.

You will learn to

Read vectors and matrices as the parts of a model
Compute gradients and run gradient descent yourself
Describe uncertainty with probability and keep numbers stable

Open course: ML Mathematics for AI Engineers

Linear algebra

Read a Model as Matrices6 lessons · 1 free
1. See a layer as a matrix and price its costFree
2. Read a matrix through its singular values
3. Find principal components from the covariance eigenvectors
4. Fit least squares and read the condition number
5. Read norms, projections and the geometry of embeddings
6. Watch distances concentrate in high dimensions

Calculus and optimisation

Differentiate and Check Gradients5 lessons · 1 free
Loading lessons. See the lessons in the course
Optimise with Gradient Descent7 lessons · 1 free
Loading lessons. See the lessons in the course

Probability and evaluation

Derive Losses from Probability6 lessons · 1 free
Loading lessons. See the lessons in the course
Evaluate with Honest Uncertainty4 lessons · 1 free
Loading lessons. See the lessons in the course

Information theory

Measure Information in Bits5 lessons · 1 free
Loading lessons. See the lessons in the course

Numerical stability

Keep Numbers Stable3 lessons · 1 free
Loading lessons. See the lessons in the course

Sampling and estimation

Sample and Estimate Expectations3 lessons · 1 free
Loading lessons. See the lessons in the course

Transformer maths

Do the Maths of a Transformer Block3 lessons
Loading lessons. See the lessons in the course

Capstone

Build and Verify a Tiny Model3 lessons
Loading lessons. See the lessons in the course
Project Derive and check a tiny language model

Deep Learning and Transformers from Scratch

9 modules · 36 lessons

Reading AI Research Papers

8 modules · 35 lessons

Inference and Serving Engineering

9 modules · 28 lessons

LLM Performance Engineering

8 modules · 36 lessons

Retrieval Engineering

9 modules · 40 lessons

Agent Tooling and MCP Engineering

7 modules · 38 lessons

Agent Reliability Engineering

10 modules · 27 lessons

AI Security and Red-Teaming

9 modules · 34 lessons

Start free

Roadmaps

Not sure what to take next?

A roadmap is an ordered path through our courses, for one goal. Each step is a full course. Open one to see the steps and track your progress.

Programming and databases in depth
3 steps
Open roadmap: Programming and databases in depth
AI Engineer
9 steps
Open roadmap: AI Engineer
AI Systems and Infrastructure
5 steps
Open roadmap: AI Systems and Infrastructure
Research Reader
3 steps
Open roadmap: Research Reader

Learn by building

Learn by building real things

Reading about something is not the same as being able to do it. The hands-on courses have you run real code on your machine, check your result against tests, and keep what you built. You understand the material because you used it.

Labs and projects
Runnable code, tests that check your result, and a written review for the parts a test cannot judge.
Results you can see
Lab tests run on your machine and report a pass or a fail you can read.
Work you keep
Your lab code and results are yours. Nothing you build is locked inside the site.
Progress you can see
A dashboard shows where you are, what is next, and a streak for the days you learn.

Templates and tools

Free templates for contest problems

Short, tested templates in C++ and Python, in three levels, developed by QFLOO. Each file says what it does, what it costs and the classic trap. Download them without paying.

Open the templatesEvery course also has free lessons, so you can read before you choose.

Community

Ask, build and show your work

Learning is easier with people around. The community lives next to the lessons, and it is moderated.

Questions on each lesson
Ask under the lesson you are reading and get an answer from the author or another learner.
Showcase
Share something you built. Every entry is reviewed before it appears.
Moderated
Posts can be reported, and reports are reviewed by a person.

Open the communitySign in to read and post.

Pricing

Start free. Pay when it helps you.

Try the free lessons with nothing at stake. If they help, pick a plan for every course we publish. Pay once with Lifetime, or pay monthly and save more the longer you commit.

Choose a plan, sign in or register, then pay. No auto-renewal: nothing to cancel. Checkout is not open to everyone yet. No refunds: try the free lessons first.

Lifetime
Best value
₹10,000
one payment, no renewal
- Every course we publish, as published
- Updates to every course
- Lab code and capstones
- Costs less than one year of Annual
Choose Lifetime
- Monthly
  Billed monthly
  ₹1,499
  Choose Monthly
- Quarterly
  Save 20%
  Billed every 3 months
  ₹3,597
  about ₹1,199 per month
  Choose Quarterly
- Annual
  Save 40%
  Billed once a year
  ₹10,788
  about ₹899 per month
  Choose Annual

Prices are in Indian rupees. The final price, with any taxes, shows before you pay. Savings compare each plan with the monthly price.
Courses are published as they pass review. Each course page shows its status.
Lifetime access lasts as long as QFLOO operates the platform. The Terms say this in full.

Start free

Free lessons first. No card needed.

From the founder

A note from me, Raju

When you are learning something hard, it helps to have someone tell you where to start and what matters. I have built many startups and worked in companies of different sizes, and along the way I read a lot of books and took a lot of courses.

I want to hand what I learned to the next generation of engineers, and to guide you as you grow. That is why QFLOO exists.

I design these courses myself, together with friends who work at large technology companies. They review the lessons, so more than one pair of eyes checks the work.

You should not have to take my word for anything. Every lesson names its sources, and every number comes from code you can run. I read each lesson and run its code before it is published.

Free lessons are open in every course. Try one, and judge the course by doing it.

Raju Kancharla, founder

Raju Kancharla on LinkedIn

FAQ

Still wondering?

Developers and ML engineers who build on language models and want the depth to measure, design and run them well. The Start here courses assume no AI background.

Learn what engineers at Google, Amazon, OpenAI, Anthropic, Microsoft, Meta, Apple and NVIDIA know.Learn what engineers atGoogleAmazonOpenAIAnthropicMicrosoftMetaAppleNVIDIAknow.

Pick your path

How CPython runs code

Objects and the data model

Concurrency

Design, test and ship

Performance

Capstone

Practice and contests

Toolkit

Complexity

Number theory

Polynomials and linear algebra

Combinatorics

Data structures

Advanced queries

Decomposition

Graphs

Trees, flows, logic

DP design

DP optimisation

Strings

Geometry

Reasoning patterns

Capstone

Storage engines

Indexes and queries

Transactions and durability

Distribution

Practice and operations

Capstone

Foundations

Production

Plan

Build

Test

Ship

How a model sees your request

Prompts that work

Giving the model facts

Calling a model in production

Failure modes and tests

Foundations

Building

Safety

Foundations

Data

Training

Evaluation

Shipping

Foundation models

Requirements and cost

Architecture and retrieval

Serving path

Reliability, tenancy and safety

Quality, observability and rollout

Capstone

Linear algebra

Calculus and optimisation

Probability and evaluation

Information theory

Numerical stability

Sampling and estimation

Transformer maths

Capstone

Networks and backpropagation

Training and scale

Text as tokens

Attention and transformers

Adaptation

Capstone

Judge and rebuild

Papers by decision

Reproduce and decide

Capstone

How inference works

Memory and the KV cache

Scheduling and compression

Scaling out

Operations

Learn what engineers at Google, Amazon, OpenAI, Anthropic, Microsoft, Meta, Apple and NVIDIA know.