Piyush Choudhari
ai & backend engineer agents · backend · cloud
Experience
-
AI Builder Intern Flytbase
-
+ FB Copilot
- Built an AI assistant piloted across 10+ organizations for querying live drone operations and creating mission workflows through natural language, reducing setup time from ~5 minutes to under 30 seconds
- Designed a 6-stage planning pipeline for intent classification, parameter extraction, entity resolution, validation, planning, and operator confirmation before execution
- Built an 8-tool ReAct assistant using LangChain and Qdrant to answer grounded questions about fleets, telemetry, docks, missions, and alarms in under 5 seconds
- Developed a 300-case evaluation suite covering routing, parameter extraction, entity resolution, and rejection of unsupported or fabricated requests
-
+ Thermal Radiometric Inspection Tool
- Built a DJI radiometric inspection platform with a backend that converts R-JPEG images into calibrated 640×512 temperature matrices in 150–300 ms, supporting per-pixel, region, line, histogram, isotherm, and image-comparison
-
+ FB Copilot
-
AI Engineer Intern Ronin Labs
-
+ AskRaven -
Link
- Built an AI system that analyzes live Meta Ads data to answer performance questions, audit creatives, and recommend budget and creative actions. Used across 5 brands, resulting in campaigns with 4% average ROAS improvement
- Developed a two-layer personalization system combining researched Brand DNA with performance-grounded memory, and consolidated 22 specialized tools into 15 parameterized tools
-
+ Sketchbot -
Link
- Built an image-to-sketch system deployed at 10 events and used by 1,000+ people, using FastAPI, SDXL Turbo, ControlNet, and OpenCV to cut robot drawing time from 10 minutes to under 3 minutes
- Deployed GPU inference on AWS g5.2xlarge instances, reducing infrastructure cost by 30% per region, with automated AMI/EBS recovery in under 15 minutes
-
+ OnePlus 13s Quest Quiz -
Link
- Built backend APIs for a global OnePlus campaign serving 150K+ total users and 250+ active concurrent users, maintaining response times below 120 ms with Node.js, TypeScript, TypeORM, and GCP Cloud SQL
-
+ Cefaly -
Link
- Built and optimized the pose-estimation system for Cefaly’s mobile app with 1K+ downloads, achieving 0.992 mAP50 for electrode detection and ~60 ms end-to-end mobile inference latency
-
+ AskRaven -
Link
Projects
see all-
Agent Sandboxing
A cloud coding-agent system that isolates repository work in Docker sandboxes and opens pull requests from agent-authored changes.
TypeScript · Node.js · Docker · PostgreSQL · Prisma · Oauth
-
CapyNodes
An interactive system design canvas where an AI Judge scores your architecture for scalability, reliability, and failure modes.
Python · Langchain · Groq · Django · PostgreSQL · LLMs
-
CapybaraDB
A vector database built from scratch in Python, implementing indexing, similarity search, persistence, and the full query pipeline.
Python · Pytorch · RAG · Vector Search
Writing
see all-
Building Mentis: A Memory Layer for Coding Agents
-
Sandboxing Coding Agents
-
Making Agents Play Pictionary
-
My Codebases Have an AI Receptionist Now
-
Implementing An SQS Like Message Queue System
-
How I Used PostgreSQL, Groq & Vercel's AI SDK To Create A Chatbot For My Portfolio Website
-
Designing a Deterministic, Low Latency Decision Engine with C++
-
Simulating vLLM's PagedAttention
GitHub
view profileLoading contributions…
Let's talk
Have an idea? Let's talk it through.
Want to know more about me?
22, born in Mumbai, live in Pune. Graduated this year in the month of June. Been building stuff since I was 14. I love bike riding, hiking, trails. You'll see me at a lot of tech events and meets, nothing better than being with people who share your passion.
I read a bunch of tech blogs and articles, always like to stay updated on latest tech.
I main Omarchy (arch btw.) and fafo a lot with my dev env. Currently ricing my neovim and hyprland setups, plus my pi.dev setup.