Skip to content
View sanatsingh's full-sized avatar
🎯
Focusing
🎯
Focusing
  • ETS GCC - FSL
  • Hyderabad, India

Block or report sanatsingh

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.

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
sanatsingh/README.md

AI Engineer & Tech Lead · World Models · Agentic Systems · Generative AI

LinkedIn Gmail GitHub Twitter


I'm an AI Engineer and Tech Lead focused on Agentic AI, Generative Systems, and - on the research frontier - World Models. At ETS GCC (the org behind TOEFL and GRE), I co-lead product development across agentic systems, assessment simulation, and generative AI. Previously at Deloitte USI - fine-tuning LLMs on DGX H100 clusters and shipping edge vision pipelines on Jetson AGX Orin.


🔭 Currently building

@ Work (ETS GCC)

  • End-to-end platform and framework/library for interactive assessment - spanning simulation development, skill practice, and deployment at scale
  • SLMs fine-tuned with PEFT for scoring and feedback
  • Multi-agent prompt generation, evaluation, and benchmarking systems

@ Personal

  • Actively researching and experimenting with World Models — causal, action-conditioned, intervention-aware generative systems
  • Shortlist - AI screening layer for early-stage investors; deep research agents build investor thesis profiles and deploy an AI persona to conduct structured async founder conversations, surfacing signal from noise at inbox scale

🌱 Currently exploring

  • Reinforcement Learning
  • World Models and Causal Representation Learning
  • GPU programming & CUDA optimization

✨ Research & Publications

  • [Wiley Expert Systems - SCI] MOSQUITO-NET: A deep learning based CADx system for malaria diagnosis · DOI: 10.1111/exsy.12695 · Poster @ ICML 2020 MLGH Workshop
  • [NARST 2026] Using Multi-Student, Generative AI Teaching Simulations as Practice Spaces for Facilitating Science Discussions · 2026 NARST Annual International Conference, Seattle WA
  • [Book Chapter] Zyik.ML - A CADx System, Project Innovation Contest 2021 Proceedings
  • Guest Reviewer, Multimedia Systems (Springer)

🏆 Recognition

  • #11 at VibeCon India 2025 - top 20 from 25,000 teams (Emergent), with Soumik Rakshit and Atanu Sarkar
  • Selected for Johns Hopkins CBID Covid-19 Virtual Design Challenge
  • AWS Activate - Zyik.ML (healthcare AI startup, co-founded)

💬 Happy to connect about

  • World Models, Agentic AI, or Generative Systems
  • Deep Learning research and Applied ML problems
  • Collaborations and interesting problems at the frontier of AI

📫 Reach me

Pinned Loading

  1. Medico Medico Public

    A dashboard system for doctors working in remote/assembled clinics where theycan access status & detailed health related information of different patients instantly and follow up with them (especia…

    HTML

  2. Mosquito-Net Mosquito-Net Public

    A deep learning based lightweight Computer Aided Diagnostic System with an aim of easing the weary task of detection of Malaria infected cells by examination of blood smears under microscope and to…

    HTML

  3. zyik/zyik.github.io zyik/zyik.github.io Public

    Website code for zyik.ml

    HTML 1

  4. YesItsSKM/Care4Me YesItsSKM/Care4Me Public

    SOFTWARE ENGINEERING MINI PROJECT - 5th Semester

    CSS 1