Skip to content
View punit2911's full-sized avatar
πŸš€
Shipping
πŸš€
Shipping

Sponsoring

@fenrir2608

Block or report punit2911

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
punit2911/README.md

Profile views


πŸ‘¨β€πŸ’» About Me

I'm an AI/ML engineer who builds LLM applications end to end: RAG pipelines, fine-tuned models and multi-step agents, shipped with Docker and AWS. I also teach the Full Stack AI Engineer course at DrippinAI Labs.

const punit = {
    role: "AI/ML Engineer",
    languages: ["Python", "JavaScript", "SQL"],
    focus: ["Agentic AI", "RAG", "LLM Fine-tuning", "Generative AI"],
    agents: ["LangGraph", "LangChain", "CrewAI", "n8n"],
    retrieval: ["FAISS", "Pinecone"],
    models: ["LLaMA", "Hugging Face Transformers", "Groq"],
    classicalML: ["scikit-learn", "TensorFlow", "Keras", "PyTorch"],
    deploy: ["Docker", "AWS", "Streamlit"],
    currentFocus: "Production-grade agentic AI systems",
    funFact: "There are two ways to write error-free programs; only the third one works"
};

πŸ”§ Current Work

  • πŸ”­ Ex-AI Intern at Industrial Light & Magic (ILM), Production Technology, Mumbai
  • πŸŽ“ AI Lead Instructor at DrippinAI Labs, Full Stack AI Engineer course
  • 🌱 Going deeper on agent orchestration, evaluation and LLM fine-tuning
  • πŸ’¬ Ask me about RAG, agentic AI, LLMs, Python and ML
  • πŸ“« Contact: punitgavali29@gmail.com

πŸ€– Agentic AI

I design agents as explicit state machines (LangGraph), not one giant prompt. Example flow from my recruitment pipeline:

flowchart TD
    A[Resume + Job Description] --> B[Shield: injection and hidden-text check]
    B --> C[Blind redaction: names and schools hidden]
    C --> D[Scorer A]
    C --> E[Scorer B]
    D --> F[Quote verifier: no quote, no credit]
    E --> F
    F --> G[Adjudicator]
    G --> H[Decision policy]
    H --> I{Recruiter approves?}
    I -- Yes --> J[n8n: Discord alert + candidate email]
    I -- No --> K[Held for review]
Loading
Project What it does Stack
🏭 Meridian: Evidence-Grounded Multimodal RAG Multimodal RAG for industrial maintenance documents with 8 retrieval channels, page citations, conflict resolution, claim verification and evidence-based abstention. Achieved 90% answer correctness, 100% Hit@5 and 100% abstention recall on held-out evaluation. Python, Qdrant, Docker Compose, Ollama
πŸ§‘β€πŸ’Ό HirePanel: Multi-Agent Recruitment Pipeline Multi-agent resume screener where every score needs a verified quote. Blocks prompt injection, hides names and schools, and a human approves every decision before n8n sends Discord alerts and emails. Ollama, FastAPI, n8n, Docker, MCP
🏒 Enterprise RAG Chatbot Support assistant that cut support workload by about 42%. RAG, vector DB, LLMs
πŸ₯ MedQueryDoc AI Medical document Q&A. LLaMA-2, Pinecone
🧾 Receiptorium Chatbot Fine-tuned LLaMA 3.2 assistant for a work-tracking platform. LLaMA 3.2, fine-tuning
πŸ’³ Transaction Anomaly Detection Flags suspicious financial transactions on a live dashboard. Isolation Forest, Streamlit
πŸ›‘οΈ PhisProbe Phishing link detection, published in IJNTI, IIT Roorkee Productathon finalist. Streamlit, GenAI

βš™οΈ Tech Stack


πŸ† Achievements

  • 🎯 Finalist at Productathon AI Hackathon, IIT Roorkee
  • πŸ“ Published research paper in IJNTI Journal: "PHISPROBE: Phishing Link Detection Using Streamlit and Generative AI Approach"
  • πŸ… IBM AI Engineering Professional Certificate (2024)
  • πŸŽ“ B.E. in Artificial Intelligence & Data Science, FR CRCE Mumbai (8.82 CGPA)

πŸ“Š GitHub Activity


πŸ“« Connect with Me

Pinned Loading

  1. Hirepanel Hirepanel Public

    Multi-agent resume screener where every score needs a verified quote from the resume. Runs on local open-source models (Ollama). Prompt-injection shield, blind redaction, human approval, n8n + Disc…

    Python 60

  2. meridian-multimodal-rag meridian-multimodal-rag Public

    Evidence-grounded multimodal RAG for industrial maintenance documentation, with hybrid retrieval, citations, conflict resolution, claim verification and abstention. Includes an optional tool-using …

    Python 45