Turning Freight DataInto Recovered Dollars

Operations Engineer / Data Scientist

Let’s connect See the work

about me.

I sit between operations and data. I take slow, manual audit work and turn it into models and services that run on their own and find the money carriers shouldn't have charged.

Years across ML, data engineering and DevOps
5+
Production systems I built and own
5
Addresses classified by Resi Audit
440K+
Recall on duplicate payments already on record
90%

More about me

what I do.

Things I build

Machine Learning

  • claims recovery prediction
  • fuzzy matching and ranking
  • address classification
  • validation that holds up

Production Services

  • FastAPI on Azure
  • verifiers for auditors
  • duplicate charge detection
  • backup verification

AI Tooling

  • MCP servers for RateWare and PC*MILER
  • MCP over Azure AI Search
  • a Claude Code plugin with 28 skills
  • RAG pipelines

Automation

  • Selenium + Airflow portal pipelines
  • data sync across clients
  • Airtable sync
  • integrity checks

selected work.

Featured Projects

Most of what I build lives inside freight audit. Open any project to see how it works.

Resi Audit dashboard: total addresses, processing activity, residential vs commercial split and confidence distribution
multi tenant SaaS / in production

Resi Audit

A multi tenant platform that catches carriers charging residential, liftgate and inside delivery fees on shipments that actually went to businesses and turns each one into a claim.

pythonfastapiceleryredisazure sqlreacttypescriptaksazure openai
Read more
Dupe Engine dashboard: likely duplicate payments found, recall by client, items needing attention and value by client
ML pipeline and web app / in production

Dupe Engine

A machine learning pipeline and web app that finds freight bills a company paid twice, ranks them so the real duplicates come first and hands them off so the money can be recovered.

pythonlightgbmlearning to rankazure mlfastapireacttypescriptaks
Read more
Mockup of an audit workbook: shipments rated against the contract, overcharges highlighted, with an AI audit note
AI audit skill / in production

AI Rating Engine

An AI freight audit that rates every shipment again against the client's carrier contracts, finds what was overbilled and delivers one workbook auditors use to file claims. Nothing is estimated and nothing is made up.

claudepythonmcpsmc3 ratewarepc*milerxlsxwritersql
Read more
Mockup of the claims model tracker: ROC curves for runs 9 to 14, validation checklist and top features
machine learning model / in development

Claims Recovery Model

A model that estimates which freight claims are worth pursuing, so recovery effort goes where it is most likely to pay off.

pythonmachine learning
Read more
Mockup of an AI chat calling the RateWare and PC*MILER MCP servers to check a shipment rate
MCP servers / in production

Freight Data MCPs

Two MCP servers that give Claude direct access to the freight industry's two standard data sources: SMC3 RateWare for LTL tariff rates and PC*MILER for truck miles. They're the backbone of the AI Rating Engine.

mcppythonsmc3 rateware xltrimble pc*milerrest apis
Read more
Mockup of Tally on three phones: today's numbers, where the money goes and net worth
side project / in daily use

Tally

A private money app I built for myself. It logs spending, tracks net worth, plans each paycheck, keeps an eye on the car and its loan and handles zakat and halal screening of investments.

fastapivercelsupabasepostgresplaidjavascriptpwagithub actions
Read more
Mockup of the backup verification report: share and VM results, file checks, drift and recovery points
reliability job / in production

Backup Verification

Checks every night that last night's backups would actually restore.
Mockup of a Claude Code session running an audit with three review agents, with skills, agents and hooks listed
side project / in daily use

Claude Toolkit

A Claude Code plugin tuned to my stack: 28 skills, 5 review agents and 5 hooks.
Landing page of the Diabetes Prediction System: Hope for a better tomorrow
side project / shipped

Diabetes Prediction System

A web app that predicts a person's chance of having diabetes.

All work

experience.

  1. ConData GlobalOperations Engineer / Data Scientist nov 2025 to nowOperations Engineer dec 2023 to nov 2025dec 2023 to now
  2. Pure PlatformData Scientistjan to may 2023
  3. Programmers ForceDevOps Engineerjan to aug 2021
  4. NESCOMMachine Learning Engineerjul 2018 to sep 2019
Illinois Tech campus at dusk with the Chicago skyline behind itmay 2023 / chicago, ilIllinois Institute of TechnologyMaster of Applied Science, Data Science
Bahria University Lahore campus buildingjul 2020 / lahore, pakistanBahria UniversityBachelor of Science, Computer Science
PythonFastAPI/AzureSQL/MCPLLMs/RAGAirflow/Seleniumscikit-learn/TensorFlowDocker/