viditparashar.me

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 documentation, coding and decision support — and now a full-duplex AI companion and company-wide automation at Ainoviq, Blackngreen's AI division.

The consistent lesson across all of it is that the model is rarely the hard part. What matters is the structure around it: whether the system knows when it is out of its depth, whether a decision can be explained after the fact, and what happens when it is wrong. Most of my work is that structure.

Two years shipping LLM systems into production, from August 2024
Four clinical agents built at HSI Labs; MedScribe built and deployed to two hospital chains at Plato Tech
At Ainoviq since March 2026, running three products at once and leading internal AI enablement
B.Tech Computer Science, RGPV Bhopal, 2025
Based in Gurugram, India — a full working day of overlap with EU teams, mornings with US East

viditparashar.me/faqviditparashar.me › faq › who-are-you
Who are you and what do you actually do?
FAQ
A full-stack and AI engineer. Two years of it, mostly in healthcare, now at Ainoviq — Blackngreen's AI division — where I work on an AI companion and the automation…
viditparashar.meviditparashar.me › about › what-i-dont-do
What I don't do
… no Salesforce, no data engineering at warehouse scale, and no visual design or brand work. I build with models rather than training them from scratch: an engineer who…
viditparashar.meviditparashar.me › about › how-i-work
How I work
… an AI feature is a way to measure it. Without that, every prompt change is a guess delivered with a confident tone, and the team ends up arguing about vibes. Once…

Search this site for “Vidit Parashar — full-stack engineer, applied LL”

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

Full-stack and AI Engineer · Ainoviq (Blackngreen)

Mar 2026 – present

Full-time

Built an AI companion around a full-duplex conversational model, where listening and speaking overlap rather than taking turns
Automated the hiring process, sales outreach (Meridian, our human-in-the-loop LinkedIn and email platform) and LinkedIn activity — these have produced real conversions
Run internal AI enablement: teaching engineers and non-engineers alike how to get genuinely more out of these tools rather than novelty out of them

Founding Software Architect · Plato Tech

Nov 2025 – Dec 2025

Full-time

Built MedScribe's core pipeline — speech-to-text through medical NLP to structured output — and made the architectural calls a seed-stage product has to live with afterwards
Developed end-to-end clinical documentation workflows covering SOAP notes, encounter summaries, and patient-friendly visit reports, holding medical terminology accuracy as the bar rather than fluency
Worked directly with product and clinical teams to deploy MedScribe for two large hospital chain clients across multi-specialty outpatient workflows

Software Engineer · HSI Labs

Aug 2024 – Aug 2025

Full-time

Built four distinct clinical agents on Next.js, LangChain and LLM orchestration frameworks, each with its own tolerance for being wrong and its own escalation path
Fine-tuned and deployed language models for real clinical workflows, improving diagnostic assistance accuracy and the quality of structured medical documentation
Implemented NLP pipelines that automated clinical note generation and cut physician documentation time by 40% during pilot deployments

Selected projects

MedScribe — an ambient scribe that turns a consultation into a note an EHR will accept (Plato Tech, seed-stage healthtech, 2025)

2 hospital chain clients deployed to · 3 clinical document types generated · 2 months from empty repo to hospital deployment

Next.js, TypeScript, Node.js, Python, LangChain, LLMs, PostgreSQL, AWS

Clinical Agent Suite — four AI agents for the parts of care that are actually paperwork (HSI Labs, 2025)

40% physician documentation time saved · 4 clinical agents designed and shipped · 2 academic health systems integrated

Next.js, TypeScript, Python, LangChain, LLMs, Node.js, MongoDB, PostgreSQL

Voxa — dictation that learns your words, and an assistant that can see your screen (Own product, 2026)

95%+ wake-word accuracy · 2 personalisation surfaces · 0 irreversible actions without confirmation

ElectronJS, Node.js, TypeScript, Microsoft Azure, Azure Functions, LLMs, Deepgram, Whisper

Conversational AI Platform — the layer other teams build voice and chat agents on (Own product, 2026)

Python, TypeScript, Next.js, Node.js, LangChain, LLMs, PostgreSQL, AWS

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

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

Who are you and what do you actually do?

What I don't do

How I work

Vidit Parashar

Summary

Experience

Full-stack and AI Engineer · Ainoviq (Blackngreen)

Founding Software Architect · Plato Tech

Software Engineer · HSI Labs

Selected projects

MedScribe — an ambient scribe that turns a consultation into a note an EHR will accept (Plato Tech, seed-stage healthtech, 2025)

Clinical Agent Suite — four AI agents for the parts of care that are actually paperwork (HSI Labs, 2025)

Voxa — dictation that learns your words, and an assistant that can see your screen (Own product, 2026)

Conversational AI Platform — the layer other teams build voice and chat agents on (Own product, 2026)

Technologies

Education

Rajiv Gandhi Proudyogiki Vishwavidyalaya (RGPV)

Availability

Related results

Results

Who are you and what do you actually do?

What I don't do

How I work

Summary

Experience

Full-stack and AI Engineer · Ainoviq (Blackngreen)

Founding Software Architect · Plato Tech

Software Engineer · HSI Labs

Selected projects

MedScribe — an ambient scribe that turns a consultation into a note an EHR will accept (Plato Tech, seed-stage healthtech, 2025)

Clinical Agent Suite — four AI agents for the parts of care that are actually paperwork (HSI Labs, 2025)

Voxa — dictation that learns your words, and an assistant that can see your screen (Own product, 2026)

Conversational AI Platform — the layer other teams build voice and chat agents on (Own product, 2026)

Technologies

Education

Rajiv Gandhi Proudyogiki Vishwavidyalaya (RGPV)

Availability