Skip to content
View kunwar-vikrant's full-sized avatar
15 followers · 11 following
  • BITS Pilani | MITx

Achievements

Achievement: Galaxy BrainAchievement: Pull SharkAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Galaxy BrainAchievement: Pull SharkAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Arctic Code Vault Contributor

Highlights

Block or report kunwar-vikrant

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kunwar-vikrant/README.md

Building scalable, autonomous systems at the intersection of high performance computing, generative models, reinforcement learning, and high-performance distributed infrastructure.

Highlights

  • BITS Pilani (Computer Science), MITx.
  • 5+ years production ML & distributed systems.
  • Primary stack: Python → Go, PyTorch → Flink, Kubernetes → VertexAI, Kafka, AWS.

Python PyTorch Go

Current Focus (2025–2026)

  • Scaling multimodal agents to 100k+ concurrent sessions (Ray + vLLM + custom scheduler)
  • Quantum-inspired optimization for large-scale RL.
  • Open-source distributed training primitives for Grok-scale models

Let’s Build Together

Open to:

  • Consulting on production High performance distributed Systems, ML / agentic systems
  • Research collaborations (multimodal, RL, distributed training)
  • Advisory roles for AI startups

→ kunwar.vikrant.professional@gmail.com
→ linkedin.com/in/kunwarvikrant | @wizard_kv

LinkedIn QR

"Prefer code that ships and scales over code that sparkles."

Pinned Loading

  1. AgentForge AgentForge Public

    Create single agents or robust multi-agent systems from plain English. One command plans, generates, quality‑checks, and packages a runnable agent; another runs a supervisor + workers loop.

    Python 1

  2. aivy aivy Public

    Aivy, a fully open-source voice assistant

    Python 7 3

  3. Let-s-Learn-Tennis Let-s-Learn-Tennis Public

    Using reinforcement learning techniques to train two agents to play a game of tennis and keep the ball in play

    Jupyter Notebook 2

  4. Self-Driving-Car Self-Driving-Car Public

    This repo demonstrates a real world case study.The aim of this project is to create a model which can be used to design an autonomous vehicle system.

    Jupyter Notebook 4 1

  5. Netflix-Movie-Recommendation-Engine Netflix-Movie-Recommendation-Engine Public

    This repo demonstrates a real world case study and aims to solve a business problem, that is to Predict the rating that a user would give to a movie that he has not yet rated and minimize the diffe…

    Jupyter Notebook 3

  6. Continuous-Control Continuous-Control Public

    Using reinforcement learning techniques to train an agent to maintain its position at the target location for as many time steps as possible.

    Jupyter Notebook 2