Edward Praveen

Senior ML Engineer & AI Architect. Building production-grade LLM systems on AWS.

A snapshot of what I’m focused on right now. Last updated May 2026.

Currently Building

  • Production RAG pipeline with hybrid search on AWS (OpenSearch + Bedrock)
  • Multi-agent orchestration system using LangGraph for a client RFP
  • Evaluating inference optimization strategies (quantization, speculative decoding)
  • Weekly tutorials covering ML/DL, Generative AI, MLOps, and Cloud Computing

Currently Reading

  • Machine Learning System Design Interview - Alex Xu
  • Hands-on Large Language Models - Jay Alammar

Currently Working On (Day Job)

  • Understanding client requirements and translating them into technical scopes
  • Creating RFPs with architecture recommendations and effort estimates
  • Building minimal MVPs with production-grade code for client evaluations
  • MLOps tooling: experiment tracking, model registry, and deployment automation

This page is updated monthly. Inspired by nownownow.com.