Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@vishvaRam
vishvaRam
Follow
View vishvaRam's full-sized avatar

Vishva R vishvaRam

Passionate and driven AI Engineer with 1 year of hands-on experience in building and deploying cutting-edge Generative AI solutions.

Block or report vishvaRam

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more aboutblocking 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 aboutreporting abuse.

Report abuse
vishvaRam/README.md

A highly passionate and results-drivenAI Engineer specializing inGenerative AI & Agentic AI Systems.
With1.5 years of hands-on experience across the full AI project lifecycle, I build, optimize, and deploy scalable AI-driven solutions.


🚀 Key Skills

  • Agentic AI & Orchestration: CrewAI, LangChain Agents
  • LLM Inference & Optimization: Llama.cpp Server, vLLM, Ollama
  • Generative AI Applications: Retrieval-Augmented Generation (RAG), Conversational AI, Autonomous Agents
  • Fine-tuning & Cloud Training: RunPod GPU Cloud, LoRA/QLoRA fine-tuning
  • Deployment & Frontend: Streamlit Apps, Docker, API-driven integrations
  • Cloud & Infra: AWS ECR, AWS ECS (Fargate/EC2), Task Definitions, Application Load Balancer, Auto Scaling
  • Programming Languages: Python (core), with focus on ML/AI frameworks

💼 Experience

  • 1.5 years building and deployingLLM-powered solutions in production.
  • Designed & optimizedRAG-based chatbots, knowledge assistants, and multi-agent workflows using CrewAI/LangChain.
  • Optimized inference paths withLlama.cpp/vLLM/Ollama to reduce latency and cost across multi-model deployments.
  • BuiltStreamlit dashboards and conversational UIs for rapid iteration and stakeholder demos.
  • ImplementedAWS ECR + ECS deployments with robustTask Definitions, environment secrets, autoscaling, and ALB routing.
  • Deployedfine-tuned models onRunPod Cloud GPUs, leveraging LoRA/QLoRA strategies for cost-efficient training.

🌐 Socials

LinkedInInstagram


💻 Tech Stack

Python
LangChain
CrewAI
Llama.cpp
vLLM
Ollama
Streamlit
Docker
AWS ECR
AWS ECS
RunPod
PyTorch
TensorFlow


📊 GitHub Stats




PinnedLoading

  1. Structured-Output-Examples-for-LLMsStructured-Output-Examples-for-LLMsPublic

    This repository demonstrates structured data extraction using various language models and frameworks. It includes examples of generating JSON outputs for name and age extraction from text prompts. …

    Python 2

  2. Data-Prep-for-LLM-fine-tuningData-Prep-for-LLM-fine-tuningPublic

    This repository helps prepare datasets for fine-tuning Large Language Models (LLMs). It includes tools for cleaning, formatting, and augmenting data to improve model performance. Designed for resea…

    Jupyter Notebook 1

  3. Blog-Writing-Agentic-RAG-CrewAIBlog-Writing-Agentic-RAG-CrewAIPublic

    An automated blog writing system that leverages CrewAI to create high-quality, well-researched blog posts. The project implements a multi-agent workflow for researching topics, generating content, …

    Python

  4. Fine-Tuning-LLMsFine-Tuning-LLMsPublic

    Jupyter Notebook


[8]ページ先頭

©2009-2025 Movatter.jp