Michael Ademigoke

Backend Engineer | Building with Rust, Python & Node.js | Exploring AI Engineering

[Michael Ademigoke @Mikeyl235]

@Damilolawo1a Na lie 😂 You wey go soon born, you dey form relief now 😂

[Michael Ademigoke @Mikeyl235]

@Eadwyne02 keep the work going gee

[Michael Ademigoke @Mikeyl235]

@Damilolawo1a keep working sis

[Param @ParamSiddh]

ML resources for beginners:

Python
- Introductory course: https://t.co/q3cl2vBb0Z
- ML with Python:https://t.co/bCVfDdlMMd
Maths
- Linear Algebra: https://t.co/NUWm7zen67
- Probability and Stats:https://t.co/8eN0fILjTv
Machine Theory
- ML by Andrew Ng - https://t.co/3nCimi1wT0
ML Projects
- Videos with code:https://t.co/TzHxExm9Nk
- - Hands-on practice: https://t.co/DjVS6PAP97
-ML Systems
- Made with ML: https://t.co/7VKMGsjinO
- - ML system design: https://t.co/IxtU44WP2t

[Udoh Jeremiah @udohjeremiah_]

The cycle of the modern-day developer:

1. Developer finds a problem. Researches it. Understands the problem. Thinks deeply about the solution. Finally: “I know what I need to build.”

2. Developer asks a powerful AI model to create the implementation plan.

3. Developer hands the plan to a cheaper/faster AI model to write the code.

4. A few days pass. The idea needs tweaking. A new feature is added. Something needs to be refactored.

5. Developer goes back to the powerful AI model for a new plan. Then hands that plan to the cheaper AI model.

6. Repeat.

Needs tweaking → new plan → new code.
New feature → new plan → new code.

7. A month later, Developer opens his laptop.

He can no longer clearly explain:

- What exact problem is he solving?
- Why does the architecture look like this?
- Why does this function exist?
- Why are there 14 abstractions?
- What depends on what?
- What the hell does this code do?

8. Developer gets uncomfortable. So he asks the powerful AI model to explain the codebase. Then asks the cheaper AI model to implement the recommendations.

9. Repeat steps 5 -> 4 -> 3 -> 2. Every day. Until eventually: Developer is no longer building the product. He's managing a committee of AI agents that are building a product he vaguely understands.

This is the story of the modern-day developer.

And somehow...

we call this productivity.

[Michael Ademigoke @Mikeyl235]

@WillsBlaq198155 that is the way to code bro push on ai will come later

[SCR @SCR01111]

50 Backend Projects to Become a Better Engineer 🚀

Beginner

URL Shortener
Notes API
Todo API
Weather API
Authentication Service
Blog Backend
Expense Tracker API
File Upload Service
QR Code Generator API
Email Service

━━━━━━━━━━━━━━

Intermediate

Chat Application
E Commerce Backend
Payment Gateway Integration
Job Queue System
Notification Service
Inventory Management System
URL Analytics
Rate Limiter
API Gateway
JWT Authentication Server
OAuth Server
Multi Tenant SaaS
Image Processing Service
Search Engine
Recommendation Engine
Event Booking System
Hotel Reservation API
Food Delivery Backend
Ride Sharing Backend
Real Time Collaboration API

━━━━━━━━━━━━━━

Advanced

Distributed Cache
Kafka Event Pipeline
Distributed Task Scheduler
Real Time Analytics Platform
Log Aggregation System
Video Streaming Backend
Distributed File Storage
CDN Clone
WebSocket Notification Service
Feature Flag Service
Load Balancer
Distributed Lock Service
API Rate Limiter at Scale
Search Autocomplete
AI Chat Backend
Vector Database API
CI/CD Deployment Platform
Kubernetes Operator
Distributed Message Queue
Backend for a Social Media Platform

━━━━━━━━━━━━━━

Don't build CRUD projects forever.

Build systems that make interviewers say:

"Tell me how you built this."

Bookmark this.

[Michael Ademigoke @Mikeyl235]

@0xbash1738 keep working bro

[Michael Ademigoke @Mikeyl235]

🚀 Completed my Week 1 AI Engineering project with AnalystLab Africa.

Built an AI Guest Support Assistant for ABC Hotels & Resorts using Generative AI, prompt engineering, and responsible AI practices.

GitHub:
https://t.co/GIwDuodV2l
@analystlabafric #AnalystLabAfrica

[Michael Ademigoke @Mikeyl235]

@Damilolawo1a what should you do it with before actually

[Michael Ademigoke @Mikeyl235]

@IamAroke when security scaling and maintainability problems comes they will undertstand actually

[Tech with Mak @techNmak]

These are literally the kind of LLM interview questions most candidates wish they had seen earlier.

A curated list of 50 LLM interview questions - shared by Hao Hoang.

What's covered:

Fundamentals:
→ Tokenization and why it matters
→ Attention mechanisms in transformers
→ Context windows and their tradeoffs
→ Embeddings and initialization
→ Positional encodings

Fine-tuning & Efficiency:
→ LoRA vs QLoRA
→ PEFT to prevent catastrophic forgetting
→ Model distillation
→ Adaptive Softmax for large vocabularies

Generation & Decoding:
→ Beam search vs greedy decoding
→ Temperature, top-k, top-p sampling
→ Autoregressive vs masked models

Advanced Concepts:
→ RAG (Retrieval-Augmented Generation)
→ Chain-of-Thought prompting
→ Mixture of Experts (MoE)
→ Knowledge graph integration
→ Zero-shot and few-shot learning

Math & Theory:
→ Softmax in attention
→ Cross-entropy loss
→ KL divergence
→ Gradient computation for embeddings
→ Vanishing gradient solutions in transformers

I will put the link in the comments.

[Michael Ademigoke @Mikeyl235]

I don’t know if this has happened to you guys, but I was debugging with AI and it told me the problem was “strange.”

That moment reminded me why fundamentals matter. Real engineering problems won’t always be solved by copying answers — we need to understand what we built

[Michael Ademigoke @Mikeyl235]

@IamAroke bro i am that loop the worst are projects i have faced it so badly that ai started me this is strange actually

[Smart👨‍💻 | Software Engineer @smartnakamoura]

Every backend engineer eventually needs to understand:

• Load balancing
• Caching
• Databases
• Message queues
• Rate limiting
• Microservices
• Horizontal scaling
• CDNs

You don’t need to master them overnight.

Save this list and learn one at a time.

[Michael Ademigoke @Mikeyl235]

@Pero4l nice work gee

[Michael Ademigoke @Mikeyl235]

@abhayk_01 keep the work going abhay

[Michael Ademigoke @Mikeyl235]

Built my first MCP server with Python.

Exploring how AI can interact with custom tools by creating a simple server and connecting it with Claude Desktop.

Next: adding auth, databases, and more advanced features.

Building and learning one project at a time

[Puneet Patwari @system_monarch]

I'm a Principal engineer & I passed system design rounds of Amazon, Atlassian, Walmart, Saleforce, and Deliveroo.

Trust me, learning system is not hard. Start from these fundamental concepts:

1) Load Balancing: https://t.co/3jKCLiI6vl

2) CDN: https://t.co/dxzCmm9gAf

3) Caching: https://t.co/pRgn0FTPp2

4) Cache Invalidation: https://t.co/QrfRjJ57gd

5) Rate Limiting: https://t.co/LE5ECM2tGt

6) API Gateway: https://t.co/DgU8cBDUVr

7) CAP Theorem: https://t.co/a8WydnAIxd

8) Sharding: https://t.co/XQLU6eDriD

9) Replication: https://t.co/KuDkFH0fjx

10) Partitioning: https://t.co/3WXKeZLbLa

11) Queues: https://t.co/JchEoCcFmF

12) Microservices: https://t.co/aAQfM6AWMq

13) Microservices Vs Monoliths: https://t.co/bTaIIWkPU3

14) Fault Tolerance: https://t.co/qXNBoyOqYT

15) Database Scaling: https://t.co/D2lvPm1wkB

16) Service Discovery: https://t.co/z2DpwbJBVI

17) Consistency models: https://t.co/K2r3nMcCQu

18) Eventual Consistency: https://t.co/SWiz4ckIKR

19) Distributed Transactions: https://t.co/xqL7BTJxXn

20) Leader Election: https://t.co/ApNaYSnSFj

21) Horizontal vs Vertical Scaling: https://t.co/IFuEmzMfob

22) Back of the Envelope Estimation: https://t.co/7ntEmtVggQ

23) Idempotency, Data Latency & Finale: https://t.co/fNArLx4MrW

Let me know what you'd like me to cover, would love to help :)

[SCR @SCR01111]

10 YouTube Resources Every AI / LLM Engineer Should Bookmark 📌

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

1. Andrej Karpathy — Neural Networks: Zero to Hero
https://t.co/0JzLsj5uGW

Best for:
• Neural Networks
• Backpropagation
• GPT from Scratch
• Tokenizers
• Transformers

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

2. https://t.co/CmLFBHy8lC

https://t.co/GgRKdD4BZB

Best for:
• Prompt Engineering
• RAG
• AI Agents
• LangChain
• OpenAI APIs

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

3. Hugging Face

https://t.co/L86nWnzxcU

Best for:
• Transformers
• Fine-Tuning
• Tokenizers
• Open Source LLMs
• Inference

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

4. LangChain

https://t.co/on2gYaJCr7

Best for:
• AI Agents
• LangGraph
• RAG
• Multi-Agent Systems
• MCP

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

5. AI Jason

https://t.co/Uwvj6v5nGo

Best for:
• AI Agents
• MCP
• LLM Apps
• OpenAI SDK
• Automation

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

6. AssemblyAI

https://t.co/NaeETDfOT2

Best for:
• Production AI
• Voice AI
• RAG
• LLM Applications
• AI Engineering

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

7. Sam Witteveen

https://t.co/073SAwgF7Z

Best for:
• LangChain
• LlamaIndex
• RAG
• Agents
• Vector Databases

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

8. IBM Technology

https://t.co/lX4OBsUjBw

Best for:
• Transformers
• Embeddings
• Vector Databases
• AI Concepts
• Enterprise AI

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

9. 3Blue1Brown

https://t.co/Jd8WgfNzoa

Best for:
• Linear Algebra
• Neural Networks
• Deep Learning Mathematics
• Attention Intuition

━━━━━━━━━━━━━��━━━━━━━━━━━━━━━━━━━━

10. Microsoft Developer

https://t.co/krWCaxl62j

Best for:
• Azure AI
• Semantic Kernel
• AI Agents
• Copilot
• Enterprise LLM Development

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Learning Order

1. 3Blue1Brown
↓
2. Andrej Karpathy
↓
3. Hugging Face
↓
4. https://t.co/CmLFBHy8lC
↓
5. LangChain
↓
6. Sam Witteveen
↓
7. AI Jason
↓
8. AssemblyAI
↓
9. IBM Technology
↓
10. Microsoft Developer

Bookmark this.

These resources take you from AI fundamentals to building production-ready LLM applications.