Skip to content
View Jaiman-Pandya's full-sized avatar
❕
working with cool people
❕
working with cool people
1 follower · 1 following

Highlights

  • Pro

Block or report Jaiman-Pandya

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
Jaiman-Pandya/README.md

Hey! I'm Jaiman. Double majoring in computer science and math with a minor in physics @ Northeastern. I am broadly interested in distributed systems, agents, agent evaluations, queueing theory, algorithms, and ML inference.

I am currently interning @ AllSpice.io in Summer 2026 improving agentic hardware design reviews alongside a cracked team (ex-Google/Stripe/Harvard/MIT)! I was previously at Sepal AI (YC S24) working on RL environments in Summer 2025. They were acquired by Mercor in February 2026.

In a past life, I was a competitive programmer and amateur hiker (hiked the Sarpass Trek in 6th grade!)

Distributed_w_newsprint_and_smaller

Comprehensive Tech Stack

Languages: Python, TypeScript, Java, C++, Go, SQL
Agent Frameworks: LangChain, LangGraph, LlamaIndex, PydanticAI, Langfuse, RAG
ML Inference: PyTorch, vLLM, NVIDIA Triton
Backend: FastAPI, Node.js, React, Redis, Kafka, Docker, Kubernetes, MySQL, PostgreSQL
Cloud: AWS, Azure, GCP, Ansible

Contact

I am always open to discussing technical challenges and potential collaboration opportunities For access to private repositories or detailed technical walkthroughs, please email me!

Email: jaimanpandya@email.com
LinkedIn: linkedin.com/in/jaimanpandya

Pinned Loading

  1. adaptive-feed-platform adaptive-feed-platform Public

    Adaptive Feed Platform is a simulation and visualization tool that models how reliability strategies like caching and prefetching impact performance of a large-scale content feed. It provides a lig…

    Python

  2. rl-paper-io rl-paper-io Public

    Deep RL agent trained to play a simplified version of Paper.io in a grid environment using Deep Q-Learning. The goal is to answer the question of whether an agent can learn meaningful strategies to…

    Python 1

  3. vendorwatch vendorwatch Public

    Y Combinator and MongoDB Hackathon Project. VendorWatch monitors vendor websites for changes. It pulls structured data from terms, policies, and SLAs, surfaces liability and compliance issues, and …

    TypeScript

  4. kv-raft-consensus kv-raft-consensus Public

    Distributed Key-Value Store Using Raft Consensus Algorithm. Data consistency is preserved even when individual nodes fail.

    TypeScript