Applied AI Engineer · LLM Systems · Production AI · 14 years

Building AI systems that
think and scale.

I build production-grade AI pipelines — document intelligence, LLM integration, and RAG systems — backed by 14 years of backend engineering on AWS. Most engineers add AI to their stack. I build the part that makes it trustworthy.

Shobhit Shukla

Shobhit Shukla

Applied AI engineer based in Pune, India, with 14 years across travel, logistics, food-tech, and AI document processing at companies like American Express, FedEx, and Punchh.

At Atos, I built an AI-powered invoice reconciliation pipeline using AWS Bedrock, Textract, and Python — processing thousands of documents monthly at ~94% accuracy in production.

My edge: I don't just integrate AI — I build the evaluation, fallback, and reliability layer that makes it production-safe.

  • 14 Years of production experience
  • 94% AI reconciliation accuracy in production
  • 10+ Industries shipped to production

01

AI Invoice Reconciliation Pipeline

Production system processing thousands of invoices monthly. Multi-modal — AWS Textract for clean documents, Bedrock Vision for low-quality scans — with a custom LLM-powered matching engine at ~94% accuracy.

Python AWS Bedrock Textract LLM S3 Lambda Ruby on Rails

02

Ola Maps Ruby Gem

Open-source Ruby gem wrapping the Ola Maps API. Reposted by Ola's CEO — one of the first community-built integrations for the platform.

Ruby Open Source Maps API

03

Secrets Manager Reader Gem

Ruby gem wrapping AWS Secrets Manager for Rails-idiomatic credential retrieval. Centralises secret management across microservices with zero boilerplate.

Ruby AWS Secrets Manager DevOps

AI / ML

  • Python
  • AWS Bedrock
  • LLM Integration
  • RAG Pipelines
  • pgvector
  • Groq · Ollama
  • RAGAS · LLM Evaluation
  • Prompt Engineering
  • OCR / AWS Textract

Backend

  • Ruby on Rails
  • Microservices
  • REST APIs
  • PostgreSQL · MySQL · MariaDB · MongoDB
  • Redis · Elasticsearch
  • WebSockets
  • Sidekiq

Infrastructure

  • AWS (S3 · EC2 · RDS · Lambda · CloudFront · Route 53 · IAM)
  • DigitalOcean · Heroku
  • Docker
  • Jenkins · CI/CD
  • Cloudflare
  • Git / GitHub

Testing & Monitoring

  • RSpec · FactoryBot
  • New Relic
  • AWS CloudWatch
  • React · Angular
  • JavaScript · jQuery
2020 — now

Senior Software Engineer · AI Systems

Atos

Built a production AI invoice reconciliation pipeline processing thousands of documents monthly at ~94% accuracy. Delivered backend systems for enterprise clients including FedEx and American Express.

Python · Ruby on Rails · AWS Bedrock · Textract · S3 · Lambda

2019 — 2020

Senior Backend Engineer

Punchh (PAX Technology)

Built loyalty, rewards, and offers infrastructure for restaurant chains used by millions of customers daily.

Ruby on Rails · PostgreSQL · Redis · Sidekiq · AWS

2015 — 2019

Backend Engineer

Neosoft Technologies

Built a fitness marketplace with live booking and Stripe payments, a secure video learning platform for enterprise teams, and an employee engagement tool with live Q&A and gamification.

Rails · React · Angular · PostgreSQL · MongoDB · Elasticsearch · Docker · AWS

2012 — 2015

Software Engineer

Affimintus Technologies

Built a sports betting platform with survival pools, trivia, and daily fantasy features — achieving 20% uplift in user engagement. Worked across financial, logistics, and CRM domains with a focus on real-time performance.

Ruby on Rails · React · PostgreSQL · Redis · WebSockets · Docker · AWS

2021

AWS Certified Solutions Architect

Amazon Web Services · Associate

Verified credential via Credly.

View badge ↗

Available for global opportunities.

Targeting Applied AI and LLM engineering roles in Europe, Canada, and Australia. Open to remote with US or European companies.

hi@shobhitbuilds.com ↗