Skip to content
View yashdesai023's full-sized avatar
🟢
Active
🟢
Active
3 followers · 3 following
  • Pune

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull SharkAchievement: Quickdraw

Block or report yashdesai023

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
yashdesai023/README.md

Yash Desai 🦅

Generative AI Engineer | RAG Architect | MLOps Specialist

Portfolio LinkedIn PyPI

🛡️ Core Value Proposition

I architect high-performance GenAI systems that bridge the gap between LLM research and production-grade engineering. My work focuses on Latency Optimization, Agentic Orchestration, and System Reliability.

📊 Engineering Benchmarks & Impact

Metric Result Project / Context
p50 Retrieval Latency 18.4ms vectorDBpipe + local ChromaDB
p99 Retrieval Latency 115.8ms vectorDBpipe Stress Test
Ops Reduction 80% Agentic Workflow Automation
Ingestion Throughput 42.5 chunks/s vectorDBpipe Modular Pipeline
Retrieval Precision 0.92 MRR UPSC RAG Intelligence Engine

🚀 Featured Engineering Assets

Project Role Tactical Edge
vectorDBpipe Lead Developer Modular Python package standardizing RAG across FAISS/Pinecone.
Agentic AI Workflow Architect Autonomous multi-agent system with long-term FAISS memory persistence.
UPSC RAG Intelligence Engineer Zero-hallucination academic engine optimized for dense/sparse retrieval.
Multi-Threaded Server Systems Engineer High-concurrency Java HTTP server with custom ThreadPool logic.

🛠 Technical Arsenal

  • AI Core: LangChain, CrewAI, Prompt Engineering, RAG Architectures, Agentic Workflows.
  • Data Infrastructure: Pinecone, FAISS, ChromaDB, Sentence-Transformers, SQL.
  • Backend Mastery: Python (FastAPI/Flask), Java (Spring Boot), REST APIs, Multithreading.
  • MLOps & DevOps: Docker, GitHub Actions, MLflow, CI/CD, Nix.

📈 Global Signal

stats languages

🔗 Digital Intelligence Hubs

✨ “Architecting the future of autonomous intelligence, one benchmark at a time.”

Pinned Loading

  1. vectordbpipe/vectorDBpipe vectordbpipe/vectorDBpipe Public

    A modular text embedding and vector database pipeline for local and cloud vector stores. Designed to streamline text preprocessing, embedding generation, and semantic search with multiple backends …

    Python 1

  2. agentic-ai-workflow agentic-ai-workflow Public

    A Production-Ready Multi-Agent System that reads emails, extracts tasks, generates smart replies, and remembers long-term context using Vector Memory (FAISS). Built as a flagship Generative AI proj…

    JavaScript

  3. ete-mlops-pipeline ete-mlops-pipeline Public

  4. chatbot-ai-project chatbot-ai-project Public

    An intelligent Retrieval-Augmented Generation (RAG) chatbot that leverages Google’s Gemini 2.0 Flash model and Pinecone Vector Database to provide accurate, context-aware answers for UPSC exam prep…

    Jupyter Notebook

  5. mcq-generator-ai-project mcq-generator-ai-project Public

    An intelligent application that leverages Google's Gemini Pro model through the LangChain framework to automatically generate and evaluate Multiple Choice Quizzes from user-provided documents.

    Jupyter Notebook

  6. DrishyaScan DrishyaScan Public

    DrishyaScan is a comprehensive web accessibility scanning tool that helps organizations ensure their websites are accessible to all users, including those with disabilities. The platform provides d…

    Java