Skip to content
View karankulshrestha's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@fossasia @jazzband @EddieHubCommunity

Block or report karankulshrestha

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
karankulshrestha/README.md

Hi, I'm Karan 👋

Agentic Systems · LLM Infrastructure · Backend Engineering


Coding GIF

About Me

I'm an engineer who enjoys building systems, working close to the stack, and understanding how things work underneath.

  • Building agentic harnesses and tool-driven systems
  • Working with LLMs, inference, and model serving
  • Designing backend services and distributed pipelines
  • Exploring GPU computing, CUDA, and performance
  • Writing mostly Python, with C++ for lower-level work
  • Building with Spring Boot, Docker, Kubernetes, and cloud infrastructure


Stack


What I Work On

Agentic Harnesses

Tool calling, orchestration, state, and multi-step execution.

Inference & Model Serving

Running models efficiently and building systems around them.

Backend Systems

APIs, workers, queues, databases, and distributed services.

Infrastructure

Docker, Kubernetes, GPUs, cloud workloads, and deployment.


Current Work

LLMs
 ├── Agentic Harnesses
 ├── Tool Calling
 ├── Inference
 └── Model Serving

Systems
 ├── Python
 ├── C++
 ├── PyTorch
 ├── CUDA
 └── Distributed Systems

Backend
 ├── Spring Boot
 ├── PostgreSQL
 ├── Redis
 ├── RabbitMQ
 └── Kubernetes

Pinned Loading

  1. jevpilot jevpilot Public

    This is the browser agent for automating the task on website in a fast and cheap manner.

    Python

  2. llama.cpp llama.cpp Public

    Forked from ggml-org/llama.cpp

    LLM inference in C/C++

    C++