I will build a rag pipeline on AWS bedrock for your documents and data

I
iloomnex
I
iloomnex
Iloomnex
Sommige informatie wordt in het Engels weergegeven.
build a rag pipeline on AWS bedrock for your documents and data
Volledig scherm
build a rag pipeline on AWS bedrock for your documents and data

Over deze dienst

RAG is easy to demo and hard to ship. Most "chat with your docs" projects fall apart the moment real users hit them. Retrieval returns irrelevant chunks. Citations don't track back to source documents. Context windows blow up the cost per query. Answers hallucinate because the retrieval layer was never actually tuned. The demo worked. Production doesn't.

I build RAG the way backend engineers build any production system. Start with real document chunking, not default splitters. Embeddings into pgvector or OpenSearch with a retrieval layer you can actually debug. Generation on AWS Bedrock with Claude or Titan models. Citation tracking so answers point back to source. Metadata filtering so users only retrieve from documents they're allowed to see.

I have hands-on Bedrock experience from the AWS AI and ML Scholars program plus production backend depth from 4+ years of shipping systems that handle real traffic. The retrieval and generation code is the interesting part. The infrastructure around it is the part that decides whether your RAG actually works in production.

Message me with what you want to make queryable.

  • AI engine

    • GPT
    • Langchain
    • Claude

  • Programmeertaal

    • JavaScript
    • Python
    • TypeScript

Maak kennis met Iloomnex

Iloomnex

Senior backend engineer

5,0(11)
  • Afkomstig uitPakistan
  • Lid sindsnov 2023
  • Gem. reactietijd1 uur
  • Laatste levering1 jaar

  • Talen

    Engels
Senior backend engineer, 4+ years shipping production systems. I build Node.js and NestJS backends on AWS serverless. Lambda, SQS, EventBridge, Step Functions. I handle the integrations most devs avoid: Amazon SP-API, Shopify, QuickBooks, Xero, and LLMs via Bedrock, OpenAI, and Claude. Day job is a multi-tenant HRIS and payroll platform running real traffic. On Fiverr as iLoomNex, I take on backend builds, API integrations, and AI features that need to work in production, not just in a demo. Always online. Reply in under an hour. Any timezone.

Mijn portfolio

Gerelateerde tags