Skip to content
View VandanaJn's full-sized avatar

Block or report VandanaJn

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
VandanaJn/README.md

Vandana Jain

Senior AI Engineer & Technical Instructor Building and teaching the next generation of production-grade AI systems.


📝 Professional Summary

Technical Lead and Senior AI Engineer with 20+ years of experience in large-scale enterprise systems. I specialize in Agentic AI, LLM platforms, and RAG, moving systems from fragile prototypes to secure, observable, and resilient production deployments. As an instructor, I bridge the gap between "code that works" and "architectural excellence"—empowering engineering teams to master reliable agent orchestration through evaluation-driven design and structural code boundaries.


🚀 Featured AI Portfolio

Autonomous multi-agent system built using the Google Agent Development Kit (ADK) to replace manual repository exploration with instant architectural insights.

  • The Architecture: Designed a "Root Agent" that intelligently delegates tasks to specialized sub-agents.
  • Production Focus: Implemented context window management (memory compaction) and integration testing with deterministic tool responses to prevent agent drift.

A production-grade RAG pipeline providing source-grounded reflections on meditation and inner growth.

  • The Stack: React, FastAPI, LlamaIndex, Pinecone, OpenAI GPT-4o-mini.
  • Innovation: Utilizes Sentence Window Parsing to optimize vector database ingestion, prioritizing architectural boundaries and factual accuracy over unpredictable generation.

📺 Instructional Leadership

I teach through the lens of software architecture rather than just syntax.

  • Python Decorators Finally Make Sense: Beyond basic syntax—how to use decorators as structural boundaries for resilient software. Features a self-healing @retry decorator designed to handle AI and network API instability.

🛠️ Core Technical Expertise

  • AI Orchestration: Google ADK, LangChain, LlamaIndex, Vertex AI, Multi-agent architectures.
  • Production RAG: Advanced grounding, citations, and hallucination reduction.
  • Cloud Infrastructure: AWS (Bedrock, Lambda, CDK, DynamoDB) & GCP (Vertex AI, Cloud Run).
  • Leadership: IC+ style, owning end-to-end architecture while mentoring teams to deliver measurable value.

📫 Connect With Me


“Precision over prediction. Architecture over syntax.”

Pinned Loading

  1. python-decorator-tutorial python-decorator-tutorial Public

    VandanaJn/python-decorator-tutorial

    Jupyter Notebook

  2. Repo-Navigator-AI Repo-Navigator-AI Public

    Repo Navigator AI

    Python

  3. ng12-risk-assessor ng12-risk-assessor Public

    ng12-risk-assessor

    Python

  4. python_essentials_ml_ops python_essentials_ml_ops Public

    Python + MLOps sandbox for data workflows, API dev, and testing—built during Duke’s MLOps specialization.

    Jupyter Notebook 2