Skip to content
View supraja777's full-sized avatar

Block or report supraja777

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
supraja777/README.md

Hi 👋, I'm Supraja Srikanth

Software Engineer • Backend Systems • AI & LLM Engineering

Building scalable backend systems and training LLMs from first principles


🧠 Core Expertise

Python Java Spring Boot PyTorch

Focus Areas

  • Backend Engineering (Java, Spring Boot, Microservices, REST)
  • Distributed Systems & Performance Optimization
  • Large Language Models (LLMs) & Transformer Architectures
  • Retrieval-Augmented Generation (RAG)
  • ML / AI Systems Engineering with PyTorch

🧩 Featured Projects

🔹 GPT From Scratch

🔗 https://github.com/supraja777/GPT-From-Scratch

Implemented a GPT-style language model from scratch using PyTorch, covering:

  • Byte Pair Encoding (BPE) tokenization
  • Multi-head self-attention & transformer blocks
  • Positional embeddings
  • Autoregressive training & inference pipelines

Built to deeply understand transformer internals rather than relying on abstractions.


🔹 All RAG Techniques

🔗 https://github.com/supraja777/All-RAG-Techniques

Engineered scalable Retrieval-Augmented Generation pipelines, including:

  • Dense embeddings & vector search
  • Semantic chunking strategies
  • Query rewriting & reranking
  • Contextual compression

Focused on improving retrieval quality and reasoning accuracy in LLM systems.


🔹 Dual-Agent Debate Pattern

🔗 https://github.com/supraja777/Dual-Agent-Debate-Pattern

Designed a multi-agent LLM debate framework featuring:

  • Agent orchestration & state-driven workflows
  • Memory management
  • Prompt engineering
  • Multi-round reasoning and synthesis

Explores structured reasoning and controlled argument generation using agents.


🤝 Let’s Connect

Pinned Loading

  1. ai-code-polisher ai-code-polisher Public

    AI Code Polisher is an intelligent multi-agent system that automatically refactors, documents, secures, and deploys your codebase. Powered by Groq and Llama 3, it scans projects, improves readabili…

    Python

  2. GPT-From-Scratch GPT-From-Scratch Public

    Developed a GPT-style language model from scratch using Python and PyTorch to deeply understand transformer internals. Learned and implemented all core components manually, including tokenization, …

    Python

  3. ai-agents-portfolio ai-agents-portfolio Public

    AI Portfolio Architect transforms a PDF resume into a polished, professional portfolio website using Llama 3.3, Streamlit, and LangChain, automating content, design, and deployment.

    Python

  4. resume-cover-letter-automation resume-cover-letter-automation Public

    Automates generating tailored cover letters for all jobs listed today, converts them to PDF, and emails them via Gmail API using LLMs for job-specific personalization.

    Python

  5. All-RAG-Techniques All-RAG-Techniques Public

    Built to explore and learn Retrieval‑Augmented Generation (RAG) techniques through practical implementations. Developed a collection of RAG workflows—from simple baselines to advanced methods like …

  6. llm-content-hub llm-content-hub Public

    Python