Skip to content
View Ajay9o9's full-sized avatar
🏅
Focusing
🏅
Focusing

Sponsors

@clintforester

Block or report Ajay9o9

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Ajay9o9/README.md

Hi there 👋

I'm Ajay K V (AJ), a Tech Lead and full-stack developer with 8 years of experience.

  • 🛠 Engineering & Architecture: Founding lead of a technical team specializing in AI/ML integration and cloud infrastructure. Extensive background building in Flutter, with backend and system architecture experience primarily in FastAPI, Django, and Node.js. I also build dynamic frontend interfaces using React, Angular, Streamlit, and Gradio. (And currently exploring Dart for the backend!)   
  • 🤖 AI & Local LLMs: Passionate about Machine Learning and AI. Experienced in building advanced RAG workflows, chatbots, and multi-agent orchestration. I have hands-on experience with vision models like Meta's SAM2, as well as image generation pipelines including Stable Diffusion. Deeply focused on local LLM inference, fine-tuning custom models with synthetic datasets, and CUDA optimization. Actively benchmarking architectural breakthroughs like Multi-Token Prediction (MTP) and quantization techniques (GGUF, TurboQuant, Unsloth) across frameworks like llama.cpp, MLX, and vLLM. AI-Portfolio   
  • ☁️ Cloud & DevOps: Architecting scalable, production-ready infrastructure across GCP and AWS. Experienced in provisioning compute instances, configuring VPC firewalls, and deploying containerized backends to GCP Cloud Run managed with robust worker pools. Proficient in bare-metal and Linux server administration (Debian, Nginx, SSL/Certbot).   
  • 🎙 Knowledge Sharing: I believe in building in public. Join the technical discourse on my Twitter, or visit my YouTube channel, CodingSalad.   
  • 📚 Learning & Exploring: Currently focusing on math, deepening my understanding of ML/DL concepts, and maximizing AI hardware performance on both Apple Silicon and dedicated GPU rigs.   
  • 🏋️‍♂️ Beyond the Keyboard: Strongman training (chasing that 200kg deadlift and squat!), astrophotography with my Fujifilm, and diving into Pokémon ROM hacks.

  

    
 
   - 💬 Ask me about Flutter, FastAPI, system architecture, RAG/multi-agent workflows, Stable Diffusion, and cloud/DevOps on AWS/GCP. - 📫 How to reach me: Below Links

  ### Find me on:     LinkedIn     YouTube     Twitter        
  

 

Pinned Loading

  1. llama.cpp-escha llama.cpp-escha Public

    C++ 10 4

  2. runs-on-a-3060 runs-on-a-3060 Public

    What actually runs on an RTX 3060 12GB, if you have any card with 12GB vram, this is for you as well. measured, with commands

    135 9

  3. minimax-h3-30series minimax-h3-30series Public

    For RTX 3000 series cards.

    Python 6 1

  4. Qwen3.8-showcase Qwen3.8-showcase Public

    50 one-shot websites from Qwen 3.8 27B, generated locally on a single RTX 3090.

    HTML 8