Roopiee

Mighty Sane Developer

Into AI/ML, Quant, Finance, Programming, Maths & Algo Trading.
Building, breaking & learning things along the way.

Feel free to DM

[Roopiee @roopakdev28]

Hi @X ,

I’m 22, an AI/ML Engineer Building at the intersection of AI, LLMs, Agents, Quant & maths and intelligent systems.

Also into psychology, inference, coding & developer tools.

Let’s connect if you’re building, learning, or thinking about something interesting. #connect

[Roopiee @roopakdev28]

@rkbdevir7 Hey RKB, happy to connect

[Roopiee @roopakdev28]

@RakhechaShubham Less go Shubham

[Roopiee @roopakdev28]

@ArjungondCodes @X Hey happy to connect Arjun!!

[Roopiee @roopakdev28]

Hi @X ,

I’m 22, an AI/ML Engineer Building at the intersection of AI, LLMs, Agents, Quant & maths and intelligent systems.

Also into psychology, inference, coding & developer tools.

Let’s connect if you’re building, learning, or thinking about something interesting. #connect

[Roopiee @roopakdev28]

@ReadAIRU Happy to connect AIRU.

[Roopiee @roopakdev28]

Someday I will reach 1000 followers on @x. Will repost this then.

SAVE THE DATE.

[Roopiee @roopakdev28]

@erden_xi Hey Erden, Happy to connect

[Roopiee @roopakdev28]

@Hrtktwt Hey hrithik, happy to connect

[Roopiee @roopakdev28]

@decodedbysania Less go Sania

[Roopiee @roopakdev28]

@builtwithrubel In the AI era, building is much easier now. Finding users remains a challenge, so I would go with 2nd option here.

[Roopiee @roopakdev28]

@Abidebyabid Hey Abid, happy to connect!

[Roopiee @roopakdev28]

The best advice/lifehack I received till date:

Conquer your mornings. In other words, Eat the frog first.😇

[Roopiee @roopakdev28]

Fine Tuning vs RAG, which one would you prefer ?

I have a slight bias towards RAG 😅

You can use a domain specific LLM
Update knowledge without retraining
Swap models without rebuilding everything
Easier to debug what the model actually retrieved

Fine tuning is still great when you need to change the model’s behaviour or teach it a specific task by requires alot of computation and training.

What do you reach for first — RAG or fine-tuning? 🤔

[Roopiee @roopakdev28]

@SamVale29 Hostinger

[Roopiee @roopakdev28]

@WaterEstek 😂😂

[Roopiee @roopakdev28]

What are a few things you are consciously doing consistently every single day?

[Roopiee @roopakdev28]

@MohakBajaj5 Lets connect Mohak

[Roopiee @roopakdev28]

@sam_developerr Happy to connect Sam

[Roopiee @roopakdev28]

Saw a YouTube video from an AI engineer talks talking about the next wave of voice agents.

The interesting shift is from the usual STT → LLM → TTS pipeline to actual speech-to-speech models.

OpenAI and NVIDIA are already moving in this direction, but there are still some hard engineering problems: observability, turn detection, interruptions, latency, and figuring out what actually happened inside the conversation.

The voice itself is getting good.

Now we need to make the systems reliable and configure the latency part.

https://t.co/LXKGoJjf24

[Roopiee @roopakdev28]

@manu_zurcher Yups works smooth

[Roopiee @roopakdev28]

Undefeatable Stack fr💪💪💪💪💪

[Roopiee @roopakdev28]

My Current website tech stack ⚡

• Framework — Next.js
• Language — TypeScript
• Styling — Tailwind CSS
• Backend — Python (FastAPI)
• Database — Supabase (Postgres)
• Auth — Clerk / Supabase Auth
• API Testing — Postman
• Deployment (Frontend) — Vercel
• Deployment (Backend) — Railway
• Storage — Cloudinary / AWS S3
• Analytics — PostHog / Google Analytics / Initially Vercel Analytics
• Version Control — Git + GitHub

Anything better than this ?

[Roopiee @roopakdev28]

@0xLingjieKong @X Hey kimi yes we are connected now