viditparashar.me/servicesopen to conversations

Full-time roles — an AI or full-stack engineering role where LLM work is the product, not a feature bolted on

Best for teams putting language models into something where being wrong has a cost — clinical is where I have done it, and voice is where I do it now.

What you get

  • Someone who has shipped LLM features into regulated environments, not just prototypes
  • Comfort across the whole stack, from the speech pipeline to the operator UI
  • A bias towards evaluation and explainability over demo quality
  • Willingness to own the unglamorous half: handoff behaviour, thresholds, what happens at the edge

open to conversations

Related results

  1. viditparashar.me/servicesviditparashar.me › services › llm-build

    LLM feature build — a contained piece of AI work delivered into your…

    scoped per engagement

    LLM feature build — a contained piece of AI work delivered into your codebase. Best for a team that knows what it wants built but has nobody free who has done it…

  2. viditparashar.me/servicesviditparashar.me › services › review

    AI feature review — a second opinion on an LLM feature before it reaches…

    scoped per engagement

    AI feature review — a second opinion on an LLM feature before it reaches users. Best for a team about to ship something they are slightly nervous about. A written…

  3. viditparashar.meviditparashar.me › hire

    Hire Vidit Parashar — open to interesting problems

    ContactIST (UTC+5:30)

    Currently open to interesting problems. Email viditsharma818@gmail.com — replies usually land within one working day, IST (UTC+5:30). Overlaps a full working day with…

Search this site for “Full-time roles — an AI or full-stack engineerin”

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.