Skip to content
View VikramxD's full-sized avatar

Organizations

@DreamFlux-Workspace

Block or report VikramxD

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
VikramxD/README.md

Typing SVG



Profile Views   GitHub followers   Twitter Follow


About Me

Machine Learning Engineer specializing in building robust production ML systems, with expertise in computer vision, audio processing, and generative diffusion models. I focus on optimizing inference for speed and efficiency, maximizing hardware potential, and ensuring seamless scalability.

Currently

Founding Engineer @ Dreamflux

  • AI-driven characters with layered memory structures
  • Multi-agent environments with spatial intelligence
  • Long-term contextual retention research

Previously

ML Engineer @ Playjump — Serverless diffusion & video pipelines Resident @ Lossfunk — Model compression & deployment

Active Research

  • ComfyUI Extensions
  • **Multi Agent Systems
  • Memory Systems
  • 3D Avatar Generation
  • Shader Generation

Tech Stack

Languages

Python Bash TypeScript

ML & AI

PyTorch Lightning HuggingFace sklearn CUDA

Frontend

React Tailwind Vite

Infrastructure & MLOps

Docker K8s FastAPI Actions W&B Grafana Prometheus


GitHub Stats

 

 

Contribution Activity

3D Contribution Calendar



Activity Graph

Activity Graph


Contribution Snake

github-snake

Trophies




GitHub   Twitter   Email

Pinned Loading

  1. VikramxD VikramxD Public

    About Me

    3 1

  2. Saka Saka Public

    Simple AI Video Enhancer Microservice

    Python 4

  3. claude_aws_bedrock_token_generator claude_aws_bedrock_token_generator Public

    Python 5

  4. Daifuku Daifuku Public

    Serve Text-to-Video Models in Production

    Python 7 1

  5. VEnhancer-ComfyUI-Wrapper VEnhancer-ComfyUI-Wrapper Public

    ComfyUI Wrapper for VEnhancer Model for Video-to-Video Super Resolution

    Python 12 1

  6. PicPilot PicPilot Public

    Generate Stunning Images and Craft Visual Stories for your Brand

    Python 19 7