viditparashar.me

Opinions I will defend

Held loosely enough to be argued out of, but they come up often enough to be worth stating before a call.

  • An AI feature that knows when to abstain beats one with better average accuracy.
  • Aggregate metrics hide the failures that matter. Look at the rare categories first.
  • If a decision cannot be explained after the fact, it should not have been automated.
  • Latency is a correctness property in voice. An answer that arrives too late is wrong.
  • Evaluation is part of the feature, not a phase after it.
  • The interesting problem is almost never the model.
  • Show the user the irreversible thing before you do it. That is cheaper than a better classifier.

Related results

  1. viditparashar.meviditparashar.me › experience › ainoviq

    Full-stack and AI Engineer at Ainoviq (Blackngreen) (Mar 2026 – present)

    Full-timeMar 2026 – present

    1 Mar 2026 — … human-in-the-loop LinkedIn and email platform) and LinkedIn activity — these have produced real conversions. Run internal AI enablement: teaching engineers and…

  2. viditparashar.meviditparashar.me › about › intro

    Vidit Parashar — full-stack engineer, applied LLM and voice systems

    I build AI features for domains where a confident wrong answer costs something. In practice that has meant clinical software — an ambient scribe, and agents for…

  3. viditparashar.meviditparashar.me › experience › hsi-labs

    Software Engineer at HSI Labs (Aug 2024 – Aug 2025)

    Full-timeAug 2024 – Aug 2025

    31 Aug 2025 — Designed and built a suite of AI healthcare agents — medical scribe, patient intake, clinical decision support and medical coding — and the NLP pipelines behind them.…

Search this site for “Opinions I will defend”

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.