Krish Deep Learning @Paralleldots, prev @BITS_Pilani. Interests: DL, CV, Multimodality, Medical Imaging, ML, Prog, Metal, GPUs

Hi! I’m Sri Krishna. Currently, I’m a co-founder of an AI startup working in the intersection of AI and UI-UX Design. Previously, I’ve worked as a founding engineer at ImagoAI and Paralleldots. I also collaborated with the Cognitive Vision group at Orebro Uni/Uni of Bremen. I was associated with Red Hen Lab in the Google’s SoC program for couple of years. I did my undergrad at BITS-Pilani, Goa. At Paralleldots, I mostly worked on computer vision (local features, keypoint/descriptors, few shot, fine grained, weakly supervised, object detection) applied to retail tasks. Earlier, I worked on medical imaging for the real world. Was very much interested in Multimodal ML as well before the LLM era. I listen to music a lot, and used to write about it here. Some part of this website is used to put down my thoughts and ideas into writing, so read at your own risk :)

If you want to get in touch or collaborate please reach out to me via email :).

Products

2023-Present

  • Flek AI
    • Built multiple products in the product design space
    • Figma Plugin & NPM package to sync design and frontend code
    • Diffusion based models to create product design inspirations from text prompts
    • ControlNet based models to convert layout sketches into full-fledged designs based on a design system
    • Parametrized model to generate visual design palletes for design systems from textual prompts
    • Figma Plugin to customize screens and flows based on existing UI Kits
    • Figma Plugin to generate mobile UI screens from text prompts. Using Multimodal LLMs.
    • Figma Plugin to help with UI Audits using Multimodal LLMs.
    • Understanding of design systems and generation of UI assets following design system guidelines.
    • Product design platform with following AI Copilots
      • Design System Generation, PRD Generation, Flow Generation
      • Sitemap Generation, Wireframe Generation, Design Generation & Frontend Sync

2022-2023

  • ImagoAI
    • Founding engineer, building and deploying cutting edge hyperspectral AI models for food quality estimation.

2018-2022

  • Shelfwatch
    • Pivoted from Medical AI to revenue making products.
    • Built the ML for the retail computer visionproduct from scratch to 1M+ ARR, alongside a brilliant team of engineers.

2016-2018

  • Diagnosis IO
    • Built and deployed AI models on head CT scans to help in triaging brain haemorrhage patients
  • Dentistry AI
    • Built and deployed AI models on bitewing X-rays to help in detecting tooth caries

Research

2023

  • Visual Sensemaking Needs Both Vision and Semantics: On Logic-Based Declarative Neurosymbolism for Reasoning about Space and Motion
    • Jakob Suchan, Mehul Bhatt, Srikrishna Varadarajan
    • 39th International Conference on Logic Programming (ICLP 2023), 393-395

2021

2020

2019

2018

2017

Talks

Contact