8000 adityaprakash-work (Aditya Prakash) ยท GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View adityaprakash-work's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Block or report adityaprakash-work

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
adityaprakash-work/README.md

๐‘€ซ๐‘‚๐‘€–๐‘€ฆ๐‘€ธ๐‘€ค

Hey, I'm Aditya

AI/ML Engineer. Architect. Tinkerer of brainsโ€”biological and artificial.

I specialize in building agentic AI systems that actually think, not just autocomplete. From CFG-driven LLMs to cloud-native MLOps pipelines, I design AI thatโ€™s composable, scalable, and a little dangerous (in a good way).


๐Ÿง  Currently...

  • Building multi-agent orchestration engines at FastpeerAI
  • Designing LLM pipelines that obey rules, not vibes
  • Co-developing Large Brain Models with Max Hospitals & IHBAS
  • Making EEGs do things they were probably never meant to do

๐Ÿ› ๏ธ Stuff I Build/ Will build in near future

  • โš™๏ธ HLGuidance โ†’ Grammar-constrained LLM generation
    โ†’ Built with GuidanceAI. Structured generation by leveraging Guidance's API to the fullest, a no-nonsense AI orchestration framework which gives just enough tooling to build an AI centric software without using 100s of over-engineered abstractions, coughs .. langchain .. coughs.

  • ... When I find the time to properly arrange and publish here.


๐Ÿงช Things Iโ€™ve Done

  • Refactored LLM inference with CFGs and regex, doubling context recall and slashing latency by 90%
  • Achieved 82% EEG classification accuracy for epilepsy detection in clinical settings
  • Created a neural cellular automata library 10x faster in JAXโ€”because why not

๐Ÿ“œ Academic Street Cred

  • ๐ŸŽ“ IIT Mandi | Double Major: CS & Bioengineering
    Neuroscience, deep learning, and other fun stuff.

  • ๐Ÿ“„ EEG-Depth-Image (ICPR Workshop '24)
    Depth map reconstruction from EEGโ€”donโ€™t ask how, just know it works (cosine sim: 0.81)

  • ๐Ÿ“„ Epilepsy Detection, Deconstructed (Under Review - IEEE Epilepsia)
    Tore apart the Bonn EEG dataset. Built something better.


๐Ÿงฐ My Stack

  • Languages: Python (can read my mind), Rust (just enough), C/C++ (if I must)
  • AI/ML: PyTorch, LangChain, TensorFlow, Guidance, vLLM
  • Infra: Kubernetes, Terraform, Argo, GCP, DigitalOcean
  • Extras: FastAPI (pro), MNE, YOLOv8, JAX, Pyspark

๐Ÿ† Highlights

  • ๐Ÿฅ‡ Amazon ML Challenge โ€“ AIR 18
    Cracked product categorization with a vision-language pipeline and a 0.71 harmonic F1

  • ๐Ÿง  INSERB Youth Conclave โ€“ 2nd Runner-up
    Invented a cognitive meta-language for aliens. The judges survived.


๐Ÿ”— Letโ€™s Talk


Built with AIโ„ข โ€” just like your fridge manual and LinkedIn JDs, but sassier and twice as confused.*

Popular repositories Loading

  1. OptiHive OptiHive Public

    A python package for biomimetic optimization algorithms.

    Jupyter Notebook 3 1

  2. Vision-Arcadia-IIT-Mandi Vision-Arcadia-IIT-Mandi Public

    CV hand gesture control

    Python

  3. Breast-cancer-detection-platform Breast-cancer-detection-platform Public

    Jupyter Notebook

  4. SegMerlin SegMerlin Public

    Image semantic segmentation using LightGBM

    Python

  5. tattva tattva Public

    Python

  6. NeuRythmia NeuRythmia Public archive

    A set of utilities for working with EEG data in machine learning applications.

    Python

0