Hasanul Banna Siam

PhD Candidate at University of Alabama at Birmingham | Immunology, Aging, Bioinformatics | Tyrrell Lab

[Shraddha Bharuka @BharukaShraddha]

MASTER GEN AI ENGINEERING

GENERATIVE AI ENGINEERING MASTER TREE
│
├── 1. Foundations
│ ├── What is Generative AI
│ ├── AI vs ML vs DL vs GenAI
│ ├── Types of Generative Models
│ │ ├── Text (LLMs)
│ │ ├── Image (Diffusion Models)
│ │ ├── Audio / Video Models
│ ├── Tokens & Context Window
│ └── Training vs Inference
│
├── 2. Large Language Models (LLMs)
│ ├── What are LLMs
│ ├── Transformer Architecture
│ ├── Attention Mechanism
│ ├── Pretraining (Next Token Prediction)
│ ├── Fine-tuning
│ └── Popular Models
│ ├── GPT
│ ├── Claude
│ ├── LLaMA
│ └── Mistral
│
├── 3. Prompt Engineering
│ ├── Zero-shot Prompting
│ ├── Few-shot Prompting
│ ├── Chain-of-Thought
│ ├── Role-based Prompts
│ ├── Prompt Templates
│ └── Prompt Optimization
│
├── 4. Embeddings
│ ├── What are Embeddings
│ ├── Vector Representation
│ ├── Semantic Similarity
│ ├── Cosine Similarity
│ └── Use Cases (Search, Clustering)
│
├── 5. Vector Databases
│ ├── What is a Vector DB
│ ├── Indexing (FAISS, HNSW)
│ ├── Similarity Search
│ ├── Metadata Filtering
│ └── Popular Tools
│ ├── Pinecone
│ ├── Weaviate
│ └── Chroma
│
├── 6. Retrieval-Augmented Generation (RAG)
│ ├── What is RAG
│ ├── Data Ingestion
│ ├── Chunking Strategies
│ ├── Embedding Storage
│ ├── Retrieval Techniques
│ ├── Context Injection
│ └── RAG vs Fine-tuning
│
├── 7. AI Agents
│ ├── What are AI Agents
│ ├── Tool Calling
│ ├── Memory (Short / Long Term)
│ ├── Planning & Reasoning
│ ├── Multi-agent Systems
│ └── Frameworks
│ ├── LangChain
│ ├── LlamaIndex
│ └── AutoGen
│
├── 8. Fine-tuning & Custom Models
│ ├── When to Fine-tune
│ ├── Instruction Tuning
│ ├── LoRA / PEFT
│ ├── Dataset Preparation
│ └── Evaluation
│
├── 9. Evaluation & Guardrails
│ ├── Model Evaluation Metrics
│ ├── Hallucination Detection
│ ├── Bias & Fairness
│ ├── Safety Filters
│ └── Prompt Injection Protection
│
├── 10. Multimodal AI
│ ├── Text + Image Models
│ ├── Vision Models
│ ├── Speech Models
│ └── Video Generation
│
├── 11. Model Deployment
│ ├── APIs (OpenAI, etc.)
│ ├── Backend Integration
│ ├── Streaming Responses
│ ├── Latency Optimization
│ └── Cost Optimization
│
├── 12. GenAI Architecture
│ ├── End-to-End Pipeline
│ ├── RAG Architecture
│ ├── Agent-based Systems
│ ├── Caching Strategies
│ └── Scalability Design
│
├── 13. MLOps for GenAI
│ ├── Model Versioning
│ ├── Monitoring
│ ├── Logging Prompts & Outputs
│ ├── A/B Testing
│ └── Continuous Improvement
│
├── 14. Real-World Applications
│ ├── Chatbots (Customer Support)
│ ├── AI Assistants
│ ├── Code Generation
│ ├── Document Q&A Systems
│ ├── Content Generation
│ └── AI Search Engines
│
└── 15. Career Path
├── Prompt Engineer
├── GenAI Engineer
├── AI Product Engineer
├── ML Engineer (LLM Focus)
└── AI Researcher

[Dhanian 🗯️ @e_opore]

𝗣𝘆𝘁𝗵𝗼𝗻 𝗥𝗼𝗮𝗱𝗺𝗮𝗽 𝟮𝟬𝟮𝟲

𝗕𝗮𝘀𝗶𝗰𝘀

Start with the core building blocks of Python.

🔹 Syntax & indentation
🔹 Variables & data types
🔹 Operators
🔹 Conditional statements (if/else)
🔹 Loops (for, while)
🔹 Functions

𝗗𝗮𝘁𝗮 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝘀

Learn how to store and manipulate data efficiently.

🔹 Lists, tuples, sets, dictionaries
🔹 List comprehensions
🔹 Iterators & generators
🔹 Strings & slicing
🔹 Collections module

𝗢𝗯𝗷𝗲𝗰𝘁-𝗢𝗿𝗶𝗲𝗻𝘁𝗲𝗱 𝗣𝗿𝗼𝗴𝗿𝗮𝗺𝗺𝗶𝗻𝗴

Write scalable and reusable code.

🔹 Classes & objects
🔹 Inheritance & polymorphism
🔹 Encapsulation & abstraction
🔹 Dunder (magic) methods
🔹 Dataclasses

𝗔𝗱𝘃𝗮𝗻𝗰𝗲𝗱 𝗣𝘆𝘁𝗵𝗼𝗻

Go beyond basics and write professional code.

🔹 Decorators
🔹 Context managers
🔹 Closures
🔹 Functional programming
🔹 Type hints & annotations

𝗙𝗶𝗹𝗲 𝗛𝗮𝗻𝗱𝗹𝗶𝗻𝗴 & 𝗜/𝗢

Work with files and external data.

🔹 Reading/writing files
🔹 JSON, CSV, XML
🔹 Logging
🔹 Environment variables

𝗣𝗮𝗰𝗸𝗮𝗴𝗲𝗦 & 𝗘𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁𝘀

Manage dependencies like a pro.

🔹 pip, pipenv, poetry
🔹 Virtual environments (venv, conda)
🔹 Requirements files
🔹 Packaging your own modules

𝗧𝗲𝘀𝘁𝗶𝗻𝗴 & 𝗤𝘂𝗮𝗹𝗶𝘁𝘆

Ensure your code is reliable.

🔹 Unit testing (unittest, pytest)
🔹 Mocking
🔹 Linting (flake8, pylint)
🔹 Formatting (black)

𝗪𝗲𝗯 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁

Build backend systems and APIs.

🔹 Flask
🔹 Django
🔹 FastAPI
🔹 REST APIs & authentication

𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 & 𝗔𝗜

Python dominates data and AI.

🔹 NumPy, Pandas
🔹 Matplotlib, Seaborn
🔹 Scikit-learn
🔹 TensorFlow, PyTorch

𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻 & 𝗦𝗰𝗿𝗶𝗽𝘁𝗶𝗻𝗴

Use Python to automate tasks.

🔹 Web scraping (BeautifulSoup, Selenium)
🔹 File & system automation
🔹 Task scheduling
🔹 Bots & scripts

𝗗𝗲𝘃𝗢𝗽𝘀 & 𝗗𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁

Run Python apps in production.

🔹 Docker
🔹 CI/CD pipelines
🔹 Cloud deployment (AWS, Azure)
🔹 Monitoring & logging

𝗦𝘆𝘀𝘁𝗲𝗺 𝗗𝗲𝘀𝗶𝗴𝗻 & 𝗔𝗣𝗜𝘀

Design scalable systems using Python.

🔹 REST & GraphQL APIs
🔹 Caching (Redis)
🔹 Message queues (Kafka, RabbitMQ)
🔹 Microservices architecture

𝗥𝗲𝗮𝗹-𝗪𝗼𝗿𝗹𝗱 𝗣𝗿𝗼𝗷𝗲𝗰𝘁𝘀

Apply your skills with practical builds.

🔹 REST API with FastAPI/Django
🔹 Web scraper & automation bot
🔹 Data analysis dashboard
🔹 AI/ML application
🔹 SaaS product

Mastering this roadmap will take you from beginner to a professional Python developer capable of building scalable, production-ready applications.

Get the complete Python Handbook here:
👉 https://t.co/TmMFX2s7Jm

[Priyanshu @priyanshudotsol]

btw this is the link -> https://t.co/88cKUkfqtV

[Shraddha Bharuka @BharukaShraddha]

MASTER PYTHON & DATA SCIENCE

PYTHON + AI + DATA SCIENCE MASTER TREE
│
├── 1. Python Fundamentals
│ ├── Variables & Data Types
│ ├── Operators
│ ├── Conditional Statements
│ ├── Loops (for / while)
│ ├── Functions
│ ├── Modules & Packages
│ └── OOP (Classes, Objects, Inheritance)
│
├── 2. Python for Data Science
│ ├── NumPy (Arrays, Operations)
│ ├── Pandas (DataFrames)
│ ├── Data Cleaning
│ ├── Data Transformation
│ └── File Handling (CSV, JSON, Excel)
│
├── 3. Mathematics for AI/ML
│ ├── Linear Algebra
│ ├── Probability
│ ├── Statistics
│ ├── Calculus Basics
│ └── Optimization Concepts
│
├── 4. Data Visualization
│ ├── Matplotlib
│ ├── Seaborn
│ ├── Plotly
│ ├── Dashboards
│ └── Storytelling with Data
│
├── 5. Databases
│ ├── MySQL
│ │ ├── CRUD Operations
│ │ ├── Joins
│ │ └── Indexing
│ ├── MongoDB
│ │ ├── Collections & Documents
│ │ ├── Aggregation
│ │ └── Indexing
│ └── SQL vs NoSQL
│
├── 6. Artificial Intelligence (AI)
│ ├── What is AI
│ ├── Types of AI
│ ├── Search Algorithms
│ ├── Knowledge Representation
│ └── AI Applications
│
├── 7. Machine Learning (ML)
│ ├── Supervised Learning
│ │ ├── Regression
│ │ └── Classification
│ ├── Unsupervised Learning
│ │ ├── Clustering
│ │ └── Dimensionality Reduction
│ ├── Model Evaluation
│ └── Feature Engineering
│
├── 8. Deep Learning
│ ├── Neural Networks
│ ├── Activation Functions
│ ├── CNN (Computer Vision)
│ ├── RNN / LSTM
│ └── Transformers
│
├── 9. Natural Language Processing (NLP)
│ ├── Text Preprocessing
│ ├── Tokenization
│ ├── TF-IDF
│ ├── Word Embeddings
│ └── Sentiment Analysis
│
├── 10. Generative AI & RAG
│ ├── Large Language Models (LLMs)
│ ├── Prompt Engineering
│ ├── Embeddings
│ ├── Vector Databases
│ ├── Retrieval-Augmented Generation (RAG)
│ └── AI Agents
│
├── 11. Model Deployment
│ ├── Flask / FastAPI
│ ├── REST APIs
│ ├── Docker
│ └── CI/CD for ML
│
├── 12. Cloud (AWS & Azure)
│ ├── AWS Basics
│ │ ├── EC2
│ │ ├── S3
│ │ └── Lambda
│ ├── Azure Basics
│ │ ├── Virtual Machines
│ │ ├── Blob Storage
│ │ └── Azure ML
│ └── Deployment on Cloud
│
├── 13. MLOps
│ ├── Model Versioning
│ ├── Monitoring
│ ├── Pipelines
│ └── Automation
│
├── 14. Real-World Projects
│ ├── Recommendation System
│ ├── Chatbot (LLM-based)
│ ├── Image Classification
│ ├── Fraud Detection
│ └── Resume Analyzer
│
└── 15. Career Path
├── Data Analyst
├── Data Scientist
├── ML Engineer
├── AI Engineer
└── GenAI Engineer

[Michael Guo @Michaelzsguo]

People are posting Qwen 3.6 configs that deliver fast TPS on as little as 12GB VRAM. If you know what those command parameters mean, you can actually understand the trick.

[Shanmukha Vishnu @iam_shanmukha]

Just achieved 60 tokens/sec with Qwen3.6-35B-A3B (35B MoE) on RTX 4070 12GB
Full 128k context + Q4_K_M + running agents daily.
Here’s the complete step-by-step from scratch

[Hasanul Banna Siam @Siam_01]

@above_spec I have got an RTX 5070 12GB VRAM and 32GB RAM. Any recommendation on what Qwen version and settings I should use??

[Hasanul Banna Siam @Siam_01]

How do I activate Devin Local agent in @windsurf? Is Devin available as a CLI, or is it a replacement for Cascade? Given that it is 30% token efficient.

[freeCodeCamp.org @freeCodeCamp]

If you're curious about what it takes to build an AI agent, you'll learn how in this course.

Lane teaches you how to use Python and the free Gemini API to code your own agent from scratch.

You'll learn about the agentic loop, tool calling, and fixing buggy programs - and by the end you'll have a fully functional agent.

https://t.co/uyIcjNCmGR

[Hasanul Banna Siam @Siam_01]

@zeddotdev Ipynb support. I miss this so much.

[Hasanul Banna Siam @Siam_01]

@outsource_ This is awesome! I was wondering, if it would be possible to plug-in a smaller model in LMstudio this way for speculative decoding.

[• nanou • @NanouuSymeon]

A lot of beginners learn Python or JavaScript….but skip Git.

Big mistake.

Git is one of the most useful tools you can learn as a developer because it helps you save work, track changes, and collaborate like a real engineer.

Here’s the roadmap I’d follow to learn Git from zero:

[It's FOSS @Itsfoss]

Major problem for me is that it's available for macOS only.

⭐️GitHub repo here: https://t.co/APfBiEZZSS

[Hasanul Banna Siam @Siam_01]

@jasperdevs This is totally on point.

[Rob Zolkos @robzolkos]

If you are pi-curious but don't have the time to set everything up I made https://t.co/lO7oUyKgvF for you. It's a curated starting point that gets you to an exciting, useful experience immediately, without the research and configuration tax.

[Hasanul Banna Siam @Siam_01]

@OpenledgerHQ .

[Kr$na @krishdotdev]

Here’s the app link:

https://t.co/wjpHVmjVzj

[Kr$na @krishdotdev]

@rmrf_404 GitHub - keshavbhatt/WonderWall-Packaging: Wonderwall Wallpaper manager, releases for Linux and Windows 10 · GitHub https://t.co/GdhsXipFOu

[Hasanul Banna Siam @Siam_01]

@MilksandMatcha @cerebras Building a scientific package for biologists that needs extensive validation. It will be super useful to have this at my disposal. I can use the arena worry free.

[Şerafettin Sarışen @ssarisen]

mac terminalinde kullandığım kendime göre faydalı bulduğum araçlar listesini bir arada topladım. tümü ücretsiz ve çalışmada hız kazandıran araçlardan oluşuyor.

6 tane aracın tam listesi aşağıda.