viditparashar.me/faqFAQ

What don't you do?

Game development, Salesforce, data engineering at warehouse scale, and design. I am also not a machine learning researcher — I build with models rather than training them from scratch.

Search this site for something I have not worked on and you will get an honest zero-results page. That is deliberate; a portfolio that claims everything says nothing.

More: What I don't do

Related results

  1. viditparashar.meviditparashar.me › about › what-i-dont-do

    What I don't do

    … interview. Search this site for something I have not worked on and you get a real zero-results page rather than a stretched claim. I will not take side work I cannot…

  2. viditparashar.me/faqviditparashar.me › faq › are-you-available

    Are you available for work?

    FAQ

    I am at Ainoviq full-time. I am open to hearing about roles where LLM or voice work is the actual product, and I have limited availability for side work when something…

  3. viditparashar.meviditparashar.me › projects › voxa

    Voxa — dictation that learns your words, and an assistant that can see…

    Case studyLive2026

    30 Jun 2026 — … flow of working at a desk. Typing out something you could just say, badly and slowly — and having to describe what is on your screen to something that cannot see it.…

    • 95%+wake-word accuracy
    • 2personalisation surfaces
    • 0irreversible actions without confirmation
    • ElectronJS
    • Node.js
    • TypeScript
    • Microsoft Azure
    • Azure Functions
    • LLMs
    • +2 more

Search this site for “What don't you do?”

Vidit Parashar

Full-stack and AI engineer

I build AI features for domains where a confident wrong answer costs something — mostly clinical software and voice agents.

Gurugram, India · IST (UTC+5:30) · viditsharma818@gmail.com · @viditparashar96 · in/vidit-parashar-056707225 · viditparashar.framer.website

Summary

I have spent the last two years putting large language models into production rather than into demos. Most of that has been healthcare — an ambient scribe that turns a consultation into an EHR-ready note, and a set of clinical agents deployed into university health systems — where the interesting problem is never the model, it is what the system does when it is unsure.

Experience

Selected projects

Technologies

AI and LLM systems
LLMs, LangChain, LLM orchestration, NLP pipelines, Model fine-tuning, Speech to text, Full-duplex voice, Agent orchestration, Workflow automation, Screen understanding
Languages
TypeScript, JavaScript, Python, SQL, HTML, CSS, Java
Frontend
React, Next.js, Tailwind CSS, Redux, Redux Toolkit, Zustand, ShadCN, Material UI, NextUI, Styled Components, Bootstrap, GSAP, ApexCharts, Recharts, PWA
Backend and APIs
Node.js, Microservices, Socket.io, Azure Functions, Prisma, Mongoose
Databases
PostgreSQL, MongoDB, NoSQL
Infrastructure and tooling
Microsoft Azure, AWS, Docker, CI/CD, Git, Vercel, Firebase, Appwrite, Vite, Webpack
Mobile and desktop
Swift, SwiftUI, iOS (native), ElectronJS, React Native, Ionic

Education

Availability

open to interesting problems.