Skip to content
View MohammedAhmeduddin's full-sized avatar

Block or report MohammedAhmeduddin

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
MohammedAhmeduddin/README.md

👋 About Me

whoami: Ahmeduddin Mohammed, ML & AI Engineer (MS CS, NJIT). Focus: production ML, LLM agents & RAG, causal inference, deep learning. Shipped: CareAgent, LoanLens, SessionScout, LiftLab. Open to ML, AI, GenAI and Forward Deployed roles; startups welcome.
Plain-text version
  • Who: ML & AI Engineer · MS Computer Science, NJIT · NYC metro, open to relocating anywhere in the US
  • Focus: production ML · LLM agents & RAG · causal inference · deep learning
  • What I bring to a team: I take a problem from raw data to a model, an API and a live deployment, and I audit my own work. I found 12 defects in LoanLens, a label leak in SessionScout and a biased "ground truth" in a 14M-row benchmark. Then I fixed them and added tests.
  • Looking for: ML Engineer · AI Engineer · GenAI Engineer · Forward Deployed Engineer roles, startups included
  • Contact: mohammed.ahmeduddin16@gmail.com

📈 Key Metrics

🎯 Best test AUC ⚡ Latency 📊 Largest dataset 🏥 Real records ✅ Tests 📦 Live deployments
0.958 27 ms 14M rows 39,694 623 4
SessionScout LSTM Redis-cached API LiftLab · Criteo CareAgent · CMS providers across 4 ML projects Hugging Face + GCP

🚀 Featured ML Projects

🟢 CareAgent — Multi-Agent Analysis of Medicare Billing

GitHub HuggingFace GCP API

A LangGraph supervisor routes 5 agents over 39,694 real New Jersey Medicare providers (CMS 2024, $4.78B in payments).

  • Peer comparison: providers are compared within their specialty (71 specialties) after adjusting for patient risk. It flags 1,461 outliers (3.7%), each with reasons drawn from the data, and an independent Isolation Forest agrees (outliers sit at the 96th percentile of its score vs the 48th).
  • Checked LLM summaries: every number in an LLM summary is checked against the data in code.
  • Caching: a fingerprinted cache cuts repeat requests from 4.7 s to 0.83 s with 0 tokens.

Providers Outliers Cache Tests Coverage

LangGraph OpenAI Isolation Forest FastAPI PostgreSQL GCP Cloud Run Secret Manager


🩷 LoanLens — Explainable, Fair-Lending-Aware Credit Risk

GitHub HuggingFace

An XGBoost credit-risk model on 307,511 loan applications (16M+ joined rows).

  • Calibrated: predicted default rate 0.080 vs actual 0.081.
  • Fair-lending checks: sex, marital status and age were removed at a cost of 0.004 AUC, and the four-fifths rule check passes (0.95 vs the 0.80 threshold).
  • Explanations: SHAP values become CFPB adverse-action reason codes, retrieved by RAG over 9,977 CFPB regulation chunks. Every citation and reason is verified in code.
  • Self-audit: found and fixed 12 defects.

AUC Calibration Fairness Tests Coverage

XGBoost SHAP RAG ChromaDB OpenAI dbt PostgreSQL FastAPI MLflow


🔵 SessionScout — Real-Time E-Commerce Purchase Prediction

GitHub HuggingFace

A 4-model cascade (Logistic Regression → XGBoost → LSTM → Transformer) in PyTorch on 241K sessions. The LSTM reaches 0.958 test AUC.

  • Label leak found: live-demo testing exposed a leak that marked 5,640 buyer sessions. The pipeline was rebuilt and retrained, and regression tests now guard against it.
  • Serving: FastAPI with Redis caching in Docker responds in 27 ms.

AUC Latency Sessions Tests Coverage

PyTorch LSTM Transformer XGBoost FastAPI Redis Docker HuggingFace


🟣 LiftLab — Causal Inference on 14M Real Ad-Campaign Users

GitHub

Measures how much ads caused visits and conversions on the full Criteo Uplift dataset (13,979,592 users).

  • Randomization check: the dataset isn't fully randomized. A classifier predicts who was treated (AUC 0.510, vs at most 0.5014 with shuffled labels), so the raw comparison overstates the visit effect by 39%. Cross-fitted AIPW is used as the reference instead.
  • Targeting: one quarter of users produce ~94% of the extra conversions. A Causal Forest ranks users with a held-out Qini of 0.339.
  • Validated first: every estimator is checked on simulated data with a known answer before it touches real data.

Rows Bias Qini Tests Coverage

EconML DoWhy AIPW Causal Forest scikit-learn FastAPI Streamlit


🧭 How I Build

Practice Example from my work
Audit before claiming LoanLens: an inverted SHAP sign made every denial list the applicant's strengths; found, fixed, regression-tested
Calibrate, then decide Replacing inflated scores with calibrated ones cut applicants sent away from auto-approval from 46% to 8.7%
Verify LLM output in code LoanLens checks every regulation the LLM cites against the retrieved passages; the decision still works if the LLM is down
Question the data LiftLab: a randomization check on 14M rows showed the "ground truth" itself was biased
Honest metrics CareAgent: renamed a "quality score" to a billing-pattern comparison, because Medicare billing data has no outcomes
Bound LLM cost and latency CareAgent reuses summaries keyed by a SHA-256 fingerprint of model + prompt + facts, with a 45 s time budget and per-client rate limits
Ship with CI Lint, tests and coverage gates on every pull request

🗂️ More Projects

Project Description Stack Links
AI Financial Report Analyst Breaks down the change in net income between two quarterly-report PDFs into revenue, margin, opex, tax and other drivers that fully reconcile. Optional LLM commentary is limited to those drivers, with citations from the Statements of Operations FastAPI · React · OpenAI · pdfplumber GitHub Live
AI Money Brain Personal-finance API: bank and card CSV import, LLM transaction categorization with keyword fallback, spending analytics, JWT auth FastAPI · PostgreSQL · Alembic · OpenAI · Docker GitHub
Developer Portfolio Tracker React dashboard: protected routes, search and filters, CRUD forms, skill charts, dark mode React · TypeScript · Vite · Recharts GitHub Live
User Management (NJIT course project) User and event-management service built on course base code: fixed 7 issues (JWT errors, email-verification order, password rules, logging), added profile management and 31 tests FastAPI · PostgreSQL · Docker · GitHub Actions GitHub

🛠️ ML / AI Stack

ML & Deep Learning

PyTorch scikit-learn XGBoost SHAP

LLM & Agents

LangGraph LangChain OpenAI ChromaDB RAG

Causal Inference

EconML DoWhy AIPW

MLOps & Cloud

MLflow Docker GCP GitHub Actions HuggingFace

Backend & Data

Python FastAPI PostgreSQL dbt Redis


📊 GitHub Stats




💼 Open to Roles

ML Engineer AI Engineer GenAI Engineer Data Scientist Forward Deployed Engineer

📍 Harrison, NJ · Open to relocation anywhere in the US · Remote, hybrid or on-site


Pinned Loading

  1. ai-money-brain ai-money-brain Public

    Python

  2. careagent careagent Public

    LangGraph multi-agent system for automated Medicare provider quality scoring, anomaly detection, and network recommendations · FastAPI · PostgreSQL · GCP

    Python

  3. liftlab liftlab Public

    Production causal inference engine for e-commerce promotion uplift analysis

    Python

  4. loanlens loanlens Public

    RAG-powered credit risk explainer over CFPB regulations

    Python

  5. user_management user_management Public

    Forked from WISClub/user_management

    Python

  6. sessionscout sessionscout Public

    Real-time e-commerce session conversion scoring — LSTM 0.9868 AUC · FastAPI 27ms · 121 tests · Live demo on HuggingFace

    Python