AI LLM Engineer Intern for B2B AI Start up

AI LLM Engineer Intern

Professional Summary

Results-driven AI Engineering Intern with hands-on experience in developing and optimizing Large Language Model (LLM) applications. Demonstrated expertise in implementing advanced RAG architectures, agent systems, and fine-tuning models. Strong research capabilities with a focus on innovative solutions and out-of-the-box problem-solving approaches.

About the Easework AI

https://www.easeworkai.com

https://www.linkedin.com/in/ratharamanan/

https://www.linkedin.com/company/easeworkai/?viewAsMember=true

https://youtu.be/8h9Qw08kyME?si=Hnj8A7qmwgn2xqak

What we're building:

AI solutions crafted with real procurement experience
Smart automation that reflects actual procurement workflows
Connected Data that provides recommendations for strategy decision making

Our mission is to revolutionize procurement by combining practitioner expertise with AI capabilities, delivering:
✓ Solutions that speak procurement teams' language
✓ Technology that fits real-world workflows
✓ Measurable business impact from day one

About Our Team

We're a collaborative, highly innovative team focused on building robust, scalable infrastructure for AI ML applications. We value continuous learning, knowledge sharing, and maintaining high standards in our infrastructure and processes.

Technical Skills

Core Technologies

• Programming Languages: Python (Advanced), SQL
• Deep Learning Frameworks: PyTorch, TensorFlow
• Version Control: Git

AI/ML Expertise

• Large Language Models (LLMs)

  • LLM fine-tuning and prompt engineering
  • Building custom training pipelines
  • Model evaluation and optimization

• Retrieval Augmented Generation (RAG)

  • Graph-based RAG architectures
  • Vector database integration (e.g., Pinecone, Weaviate)
  • Knowledge graph construction and querying
  • Hybrid search implementations

• AI Agents

  • Multi-agent system design
  • Agent orchestration and communication
  • Task planning and execution frameworks

Research & Development

• Conducted deep research into state-of-the-art AI technologies
• Implemented novel approaches to improve model performance
• Developed innovative solutions for complex AI challenges

Key Projects

1. Advanced RAG System

   • Implemented a graph-based RAG architecture
   • Improved retrieval accuracy by 40%
   • Integrated knowledge graphs for enhanced context understanding

2. LLM Fine-tuning Pipeline

   • Developed automated fine-tuning workflows
   • Optimized model performance for specific use cases
   • Reduced training time by 30%

3. AI Agent Framework

   • Built a scalable multi-agent system
   • Implemented task orchestration and management
   • Enhanced system efficiency through agent collaboration

**Benefits

Intern convered to Full time role in 3-6 months
Remote work options
Learn & Practice cutting edge tech
Innovate , Fail, Learn, Success & Iterate
Build word class AI platform from scratch