Skip to content
View joshupadhyay's full-sized avatar

Block or report joshupadhyay

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
joshupadhyay/README.md

Josh Upadhyay

Cloud engineer with 4 years of AWS experience, now building with AI at Fractal Tech in NYC.

At 3M I built internal platforms for R&D, led migrations of fluid modelling applications to AWS Batch. I worked with scientists and software engineers to turn issues into software solutions!

Now I'm at Fractal Tech, an AI accelerator, building GPU pipelines on Modal, shipping full-stack AI apps with Claude's API, and writing publicly about inference infrastructure.

I'd like to talk to clients, build infrastructure, and see immediate impact of my work. I'm targeting forward-deployed and solutions engineering roles at infra companies, where client sense and technical ability intersect.


My Projects

Extemp – Impromptu speaking coach. Record a 2-minute speech, get structured feedback on clarity, filler words, and delivery. Built with Groq (Whisper transcription) + Next.js.

What's the Busiest Citibike Station? – 20 GB NYC Citibike dataset processed in 137s using Modal's parallel fan-out. An exploration of serverless GPU compute for large-scale data work, and how easy it is with Modal's functionality. Deployed using modal serve.

Fine-tuning Stable Diffusion – Fine-tuned SDXL on Edward Hopper's painting style. Covers the full pipeline: training, cold-start optimization, and serving a custom image model from Huggingface. Explores caching, GPU snapshots, and other optimization techniques.

NYC Gaussian – 3D reconstruction of St. Mark's Place using gaussian splatting algorithms on Modal GPUs. Converts Street View imagery into an explorable 3D scene in the browser. I generated my own Gaussians with AnySplat, and the PoC is available here.

The Crunch – AI-powered night-out planner for NYC. Claude tool calling + Mapbox for real-time venue recommendations, deployed on AWS EC2 with CI/CD via GitHub Actions.

Interior Bot (in progress) – Fine-tuning Qwen 2.5 7B on interior design using expert trajectories distilled from Claude. A ReAct agent + ChromaDB vector search, inspired by Databricks' KARL paper — small model, domain-specific retrieval, frontier-model quality at a fraction of the cost.


Stack

AWS (Lambda · ECS · Batch · CDK) · Docker · TypeScript · Python · Modal · GitHub Actions · Next.js


Connect

Pinned Loading

  1. fastai-v3 fastai-v3 Public template

    Forked from render-examples/fastai-v3

    Starter app for fastai v3 model deployment on Render

    Python

  2. airline_tweet_classification- airline_tweet_classification- Public

    Data from Kaggle, models made using fast.ai

    HTML

  3. dream_journal dream_journal Public

    Dream Journal App for COMP 225 at Macalester College

    Dart