KAHA SE PADHE ?

ONE STOP SOLUTION

LMT CDAC CCAT Study Materials ( Videos + Notes )

Videos Lectures
Dedicated Notes For CCAT Syllabus
Practice Problems
Mock Test
 AI Engineer Roadmap

📌 What AI Engineers Actually Do ?

📌 Detail AI Engineer Roadmap
Topic wise Syllabus

Free Resources

Timelines

How to Get a Job

 What AI Engineers Do ?
📌 Company: A bank wants to reduce waiting times for customer inquiries.
📌 Problem: Customers have to wait a long time to talk to human agents.
📌 AI Engineer’s Work:
Collect Data: Gather past customer chats and FAQs.

Train an NLP Model: Use deep learning (like GPT) to make the chatbot understand customer

queries.

Fine-Tune & Test: Train it to respond accurately and politely.

Deploy & Integrate: Connect the chatbot to the bank’s website & mobile app.

📌 Impact: The chatbot answers 80% of common questions instantly, reducing workload for
human agents and improving customer satisfaction.
 1. Computer Science Fundamentals - 4 Weeks

Basics of Computing – What computers are, how they work, hardware vs. software.

Binary System – Understanding how computers use 0s and 1s to process data.

Algorithms & Flowcharts – Basic logic and step-by-step problem-solving techniques.

Programming Basics – variables, strings, and numbers, if condition, loops.

Operating Systems – Understanding Windows, Linux, macOS, and how they manage resources.

Computer Networks – Basics of the internet, IP addresses, protocols (HTTP, TCP/IP).

DBMS and DSA - Basics of DBMS

Resources : KHAN Academy Course and CS50

 2. Python [ 6 Weeks ]

Basics - 4 Weeks Advance - 2 Weeks

Variables, Numbers, Strings Inheritance, Generators, Iterators

Lists, Dictionaries, Sets, Tuples List Comprehensions, Decorators

If condition, for loop Multithreading , Multiprocessing

Functions, Lambda Functions

Modules (pip install) Resources :

Read, Write files Code Basics Python Playlist

Free Code Camp
Exception handling
Code with Harry
Classes, Objects
Apna College
3. Data Structures - 2 Weeks Resources : Code Basics DSA with Python

Data structures basics, Big O notation

Data structures: Arrays, Linked List, Hash Table, Stack, Queue

Data structures: Tree, Graph

Algorithms: Binary search, Bubble sort, quick sort, merge sort

Recursion

4. SQL - Database - 2 Weeks

Basic SQL Command [ SELECT , INSERT , UPDATE , DELETE ]

Joins , Sub Queries , Aggregation [ GROUP BY , HAVING ]

Indexing and Optimization

Resources : Riti Kumari , Khan Academy SQL Course , Code Basics

 5. Version Control - GIT and GITHUB [ 1 Week ]
How do you Collaborate with the team? | How do you share code with the team? | How do you review their code?

Introduction – What is Version Control? Why use Git & GitHub?

Basic Commands – git init, git add, git commit, git push, git clone

Branches & Merging – Creating, switching, merging branches, resolving conflicts

Undoing Changes – git revert, git reset, git checkout, understanding HEAD

Collaboration – Forking, pull requests, code review on GitHub

Resources :

Kunal Kushwaha
Apna College
Free Code Camp
Code with Harry
Code Basics & Corey Playlist
 6. Mathematics for AI [ 3- 4 Weeks ]
Linear Algebra
Data Visualization & Discrete Math
Vectors, Matrices, Eigenvalues, and Eigenvectors
Histograms, Pie Charts, Bar Charts, Scatter Plots
Matrix Operations (Transpose, Inverse, Determinant)

Calculus Graph Theory (Nodes, Edges, Paths)

Basics of Integral and Differential Calculus Boolean Algebra & Set Theory

Partial Derivatives & Gradient Descent Optimization Techniques

Probability & Statistics Loss Functions & Cost Functions

Descriptive vs Inferential Statistics Convex Optimization

Continuous vs Discrete Data, Nominal vs Ordinal Data Gradient-Based and Non-Gradient Optimization

Measures of Central Tendency (Mean, Median, Mode)

Measures of Dispersion (Variance, Standard Deviation)

Resources :

Probability Basics & Distributions (Normal, Binomial, Poisson)

1Blue 3Brown
StatQuest with Josh Stammer
Correlation and Covariance
Khan Academy Mathematics and
Central Limit Theorem Statistics Course
Hypothesis Testing (p-value, Confidence Interval, Type 1 vs Type 2 Mathematics for Machine Learning [
Coursera Deep Learning.io ]
Error, Z-test)
7. Data Visualization - 1-2 Week
NumPy (Arrays, Broadcasting, Matrix Operations)

Pandas (DataFrames, Cleaning, Transformations)

Matplotlib & Seaborn (Data Visualization)

Resources : YT Playlist and One Shot Videos

8. EDA - Exploratory Data Analysis (1 Week) - P

Goal: Develop skills to explore and analyze datasets effectively.

Handling missing values

Data visualization (histograms, boxplots, scatter plots)

Feature engineering and scaling

Resources : EDA using Kaggle YT Project Videos

Assignment : Practice on atleast 3 Kaggle Dataset
 10. MLOPS - [ 1 Weeks ]

What is API? FastAP| for Python server development

DevOps Fundamentals: CI/CD pipelines, containerization (Docker, Kubernetes)

Familiarity with at least one cloud platform (AWS, Azure etc.) [ Amazon Sagemaker ]

Assignment :
Resources : Code Basics
ML Projects with Deployment : Build End to End
FASTAPI Tutorial Playlist
Projects
Docker Tutorial Playlist
Data collection and Data cleaning

Model building and model training

Model Deployment [ on Cloud like AWS ]

 11. Deep Learning - [ 2- 3 Weeks ]
Deep Learning is the fundamental of LLM and gen AI

Neural Networks & Backpropagation – Core mechanism behind deep learning.

Optimization Algorithms – SGD, Adam, RMSprop for efficient training.

CNNs & Transformers – Key architectures for computer vision and NLP.

Regularization Techniques – Dropout, Batch Normalization to prevent overfitting.

Model Deployment & Scalability – TensorFlow, PyTorch, Docker, multi-GPU training.

Assignment :
Learn this with building project ( tensor flow and pytorch )

Resources : Code Basics

Tensor Flow Playlist & Pytorch Playlist Code Basics

End to End Deep Learning Potato Disease Classification
Projects by Code Basics
 12. NLP - LLM - LangChain [ 4- 6 Weeks ]
LangChain (LLM-based Application Development)
NLP (Natural Language Processing)
1. LLM Wrappers & Pipelines – Integrating OpenAI, Hugging Face, and local
Tokenization & Embeddings – WordPiece, BPE, Word2Vec, GloVe, FastText.
models.
Sequence Models – RNNs, LSTMs, GRUs, Transformers.
2. Prompt Templates & Chains – Sequential and agent-based workflows.

Attention Mechanism – Self-attention, Multi-head attention. 3. Memory & Context Handling – Conversational memory for chatbots.

Preprocessing & Text Augmentation – Stemming, Lemmatization, Stopword Removal. 4. Retrieval-Augmented Generation (RAG) – Using vector databases like FAISS,

Pinecone.
NLP Tasks – Named Entity Recognition (NER), Text Classification, Sentiment Analysis,
5. Tool Integration – APIs, databases, web scraping, function calling with LLMs.
Machine Translation.

LLM (Large Language Models)

Transformer Architecture – Foundation of BERT, GPT, T5, LLaMA.

Pretraining & Fine-tuning – Supervised fine-tuning, RLHF (Reinforcement Learning with

Human Feedback).

Prompt Engineering – Zero-shot, Few-shot, Chain-of-Thought (CoT) prompting.

Model Scaling & Optimization – Parameter-efficient tuning (LoRA, adapters).

Bias, Safety & Explainability – Ethical AI, hallucinations, factual consistency.