Skip to content
View vkrishna1084's full-sized avatar

Block or report vkrishna1084

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 is supported. 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
vkrishna1084/README.md

Vamshi Krishna Enabothala

Principal AI Architect @ Pinecone · prev. Sr. Applied AI Specialist @ AWS Data Labs · 14 years shipping production AI systems

I help enterprises take AI from demo to production — retrieval and vector search, RAG and agent architectures, MLOps, and rigorous model evaluation. 52+ enterprise engagements led across financial services, insurance, media, defense, and research.

🌐 Site & free AI consultations: vamshienabothala.com (update once live) ✍️ Writing on: vector search · agentic retrieval optimization · AI model evaluation 💼 LinkedIn: linkedin.com/in/vkenabothala


Selected public work

Engagement What happened
🛰️ MIT Lincoln Lab (LADI) — disaster response CV Human-in-the-loop imagery pipeline: 100K images triaged in 18 minutes instead of 42 daysAWS ML Blog
🐋 Project CETI — decoding whale communication Lead ML Architect (volunteer); presented at AWS re:Invent 2022 with founder David Gruber
🎖️ RallyPoint — veteran job recommendations Personalized job matching for the military community → AWS ML Blog
📰 Thomson Reuters — content personalization Subscription-plan personalization at global-publisher scale → AWS ML Blog
⚙️ VMware — MLOps from scratch End-to-end pipeline with GitLab + MWAA + SageMaker → AWS ML Blog
🏦 Genworth — serverless ML Fully serverless ML pipeline for a regulated insurer → AWS ML Blog

🏆 1st place, Pinecone/AWS Generative AI Hackathon — real-time disaster imagery annotation & geospatial search 🎤 Keynote, US Navy AI/ML Annual Conference · AWS Senior Speaker certified


What I'm building & writing about

  • Retrieval quality in practice — what actually moves the needle: chunking, embedding choice, metadata filtering, reranking
  • Agentic retrieval — why decomposed sub-queries lose entity/time context, and architectures that fix it
  • Honest evaluation — sealed benchmarks, pre-registered success criteria, and hallucination measurement for RAG and fine-tuned models

Certifications

AWS ML Specialty · AWS Big Data Specialty · AWS Solutions Architect · CCA Spark & Hadoop Developer


💬 Working through a hard retrieval/RAG/agent problem? I offer free 20-minute consultations — booking link on my site.

Popular repositories Loading

  1. golden-hour-geospatial-search golden-hour-geospatial-search Public

    Python 1 3

  2. streamlit-langchain-template streamlit-langchain-template Public

    Python 1

  3. examples examples Public

    Forked from pinecone-io/examples

    Jupyter Notebooks to help you get hands-on with Pinecone vector databases

    Jupyter Notebook

  4. vkrishna1084 vkrishna1084 Public

    Vamshi profile repo