Abhin Krishna profile portrait
Researcher · Developer · Engineer

Abhin Krishna

Exploring the intersection of human and artificial intelligence

I build at the boundary of biological brains and computational intelligence, advancing neural decoding, training deep neural nets, and AI-driven medical systems. Driven by curiosity and a builder's mindset, I love hardware prototyping, startup ideas, and shipping open-source projects.

Skills

The tools and technologies I work with across AI, neurotech, embedded hardware, and the web.

AI & Neurotech

JAX TensorFlow MNE-Python (EEG) Edge Impulse OpenCV

Languages & Hardware

Python C / C++ JavaScript ESP32S3 Linux / Shell

Web Stack

React / Next.js Supabase Three.js

Projects

Open-source contributions and hardware prototypes combining digital signal processing, Edge AI, and web technology.

Deep Learning & BCI

EEG Motor Imagery Classifier

Engineered an end-to-end pipeline to classify 4-class motor imagery (hand/foot movement intents) using the EEGNet architecture. Implemented MNE-Python for ICA-based artifact removal, establishing critical performance baselines in BCI experiments.

Edge AI & Hardware

TinyML Object Detection

Deployed a real-time computer vision detection system on an ESP32-S3 Sense board. Optimized a quantized MobileNet V2 model using the FOMO algorithm, reaching 7 FPS at 143ms latency for industrial parts sorting.

Open-source NLP

LipiPala AI

Contributing to an open-source initiative dedicated to preserving and revitalizing endangered Indian languages. Combining NLP, speech recognition, and LLMs to create accessible linguistic analysis tools.

Web Utility

Gemini Sparkle Remover

A high-performance, client-side tool for removing sparkle watermarks from images generated by Google Gemini AI. Uses a mathematically precise Reverse Alpha Blending algorithm to restore original pixels with zero quality loss.

Professional Experience

Research internships, open-source leadership, and engineering roles.

Executive
FOSSMEC, Model Engineering College
Full-time Jun 2025 - Present
Kochi, Kerala · On-site

Leading workshops, mentoring students, and driving open-source culture at Model Engineering College.

  • Served as Lead Instructor for Let's Git It, a 2-day workshop on Git workflows, branching, and portfolio hosting via GitHub Pages.
  • Assisted in the Linux Installation Workshop, guiding students through dual-boot and VirtualBox setups.
  • Handled registration and marketing for Code-A-Pookalam 2025.
  • Assisted in organizing Build It Up, a 2-day hands-on DBMS workshop using Supabase, Express.js, and Next.js.
  • Volunteered in marketing and coordination for Devsprint, a one-day open-source sprint.
  • Co-led interview and screening for first-year applicants, onboarding the next generation of FOSSMEC trainees.
United Kingdom · Remote

Worked at Tencent AI Lab on ML, NLP, and LLM research for open-source AI model development.

  • Researched and implemented Computer Vision architectures for 3D reconstruction.
  • Fine-tuned and aligned Large Language Models (LLMs) to improve mathematical reasoning capabilities.
  • Studied optimization techniques for deep neural networks.
  • Collaborated with senior research scientists to draft and submit papers to CVPR and NeurIPS.
Toronto, Canada · Remote

Developed the website for a decentralized marketplace built on the TON blockchain.

  • Built and deployed the full frontend for a TON blockchain-based decentralized marketplace.
  • Integrated wallet connection flows and on-chain transaction UI components.
  • Worked remotely with a distributed team across Canada and Europe.

Publications

Research preprints and academic contributions in computational neuroscience and AI.

Preprint Mar 30, 2026

A Comparative Study of Hodgkin-Huxley and Izhikevich Models for High-Fidelity Neural Spike Prediction

Abhin Krishna  ·  Computational Neuroscience  ·  Neural Modelling

Read PDF

A rigorous comparative analysis of two foundational computational neuroscience models: the biophysically detailed Hodgkin-Huxley model and the computationally efficient Izhikevich model, evaluated for their accuracy in predicting high-fidelity neural spike trains across varied stimulation conditions.

#ComputationalNeuroscience #Hodgkin-Huxley #Izhikevich #NeuralSpike

Honors & Highlights

Selected milestones demonstrating academic rigour, research, and global engagement.

HPAIR 2025 Delegate

Selected for the prestigious Harvard Project for Asian and International Relations Conference.

Brain Modeling

Completed computational systems neural circuit modeling training at CNS Lab, IIT Madras.

Ideathon Award

Presented "PhytoScan", an AI-driven fruit freshness detection device at Money Conclave.

German Proficiency

Goethe Zertifikat B1 certified speaker in German language with a score of 82.

Start Collaboration
Available for Research & Startup Collaborations

Let's Connect

I am actively looking for co-founders, research collaborators, and start-up connections. If you want to discuss BCI, neural systems modeling, or start-up ideas, let's talk.