Skip to content
View JDede1's full-sized avatar
🎯
Focused
🎯
Focused
  • 01:44 (UTC -12:00)

Block or report JDede1

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
JDede1/README.md

👋 Hi, I'm Ajibola Jeremiah Dedenuola, M.Sc.

Data Scientist • Machine Learning Engineer (Applied ML | MLOps | Cloud)

📧 Email💻 GitHub🔗 LinkedIn


🧭 Quick Overview


🚀 About Me

I’m a Data Scientist & Machine Learning Engineer who builds reproducible, scalable, and cloud-ready ML systems. My focus is on:

  • End-to-end ML pipelines (training → evaluation → deployment → monitoring)
  • Cloud ML deployment using Vertex AI & Cloud Run
  • Experiment tracking & registries using MLflow
  • Containerized training + inference with Docker
  • Automated workflows using Airflow
  • Data validation & drift detection using Evidently AI

Across my roles, my work has consistently centered on clean data, reliable pipelines, and production-grade ML systems.


🧭 Career Journey

Manifest & Company Inc. — Applied ML & MLOps (2025–Present)

Design, deploy, and maintain cloud-based ML systems using Vertex AI, Cloud Run, MLflow, Docker, and Airflow.

  • Built reproducible training & evaluation pipelines on Vertex AI
  • Containerized preprocessing, training, and inference workflows
  • Implemented experiment tracking + model registry with MLflow
  • Automated batch inference, retraining & feature workflows with Airflow
  • Added monitoring & drift detection workflows using Evidently AI
  • Integrated CI/CD workflows using GitHub Actions

Canada Revenue Agency — Data Quality & Compliance Analytics (2021–2024)

  • Created validation logic reducing manual review by ~25%
  • Reconciled multi-system financial datasets
  • Built anomaly detection pipelines for compliance classification
  • Standardized audit-ready reconciliation workflows

Northland Properties — Data Operations & Analytics (2017–2021)

  • Automated SQL/Excel workflows (40% reduction in manual reporting)
  • Consolidated cross-property data for analytics pipelines
  • Built KPI dashboards & standardized data definitions

🌟 Pinned Projects (Selected)


📂 Featured Projects

🏦 Loan Default Prediction — End-to-End MLOps Pipeline

Tech: XGBoost, MLflow, Docker, Airflow, Vertex AI, Evidently AI, Optuna

  • Full MLOps pipeline: preparation → training → evaluation → deployment → monitoring
  • Deployed on Cloud Run with MLflow registry integration
  • Automated batch inference & drift detection in Airflow

🧠 RAG System for Banking FAQs — Retrieval-Augmented Pipeline

Tech: SentenceTransformers, FAISS, FastAPI, Streamlit, Phi-3 Mini

  • Modular ingestion → embedding → retrieval → generation pipeline
  • FAISS-optimized retrieval with evidence tracing
  • Streamlit UI with reliability features

🧾 Transformer Fine-Tuning — RoBERTa & BART

  • Classification + generative explanation tasks
  • ~0.93 accuracy & strong BLEU/ROUGE metrics

📊 Credit Risk Classification — ML Modeling Pipeline

  • Achieved ~90% accuracy / 96% recall using engineered features
  • Interpretable feature importance & risk drivers

🛠️ Tech Stack

👩‍💻 Languages & Core Libraries

Python NumPy Pandas Matplotlib Seaborn


🤖 Machine Learning & Deep Learning

Scikit-learn XGBoost PyTorch Keras Hugging Face


🧠 NLP / LLMs & RAG

Transformers SentenceTransformers FAISS FastAPI


🏗️ MLOps, Pipelines & Orchestration

MLflow Apache Airflow Docker Terraform


☁️ Cloud & Deployment (GCP)

Google Cloud Vertex AI Cloud Run Cloud Storage


🧩 Data Engineering & Databases

BigQuery SQL ETL Pipelines


📈 Monitoring & Evaluation

Evidently AI Logging & Metrics


⚙️ Version Control & Dev Tools

Git GitHub GitHub Actions VS Code


🎓 Education

M.Sc. in Information Science (Machine Learning Focus) — University of Arizona (2023–2025)

GPA: 3.78 / 4.00
📜 Official Degree Verification

Post-Baccalaureate Diploma — Human Resources Management

Thompson Rivers University

B.Sc. Zoology — University of Ibadan


🏆 Certifications

DataTalks.Club — MLOps Zoomcamp Certificate | Aug 2025
View Credential

Oracle — Oracle Certified Foundations Associate: AI Foundations | Oct 2025Oracle Cloud Infrastructure (OCI)
View Credential


📫 Connect With Me

I'm open to opportunities in ML Engineering, Data Science, and MLOps across Canada & the U.S.

📧 Email: ajdedenuola@gmail.com
💼 LinkedIn: https://www.linkedin.com/in/jeremiah-dedenuola
💻 GitHub: https://github.com/JDede1
📄 Résumé: View PDF


Thanks for visiting! My work focuses on building ML systems that are transparent, reliable, and production-ready.

Pinned Loading

  1. loan_default_prediction loan_default_prediction Public

    End-to-end MLOps pipeline for loan default prediction using Airflow, MLflow, Vertex AI, Cloud Run, and Terraform.

    Python 1

  2. data-analysis-visualization-assignment-4 data-analysis-visualization-assignment-4 Public

    INFO 526 — Data Analysis and Visualization, Assignment 4 (Cluster & PCA Analysis of Angry Birds Personality Data). Part of the Master’s in MIS/ML program at the University of Arizona. Uses K-means …

    Jupyter Notebook

  3. data-analysis-visualization-assignment-5 data-analysis-visualization-assignment-5 Public

    INFO 526 — Data Analysis and Visualization, Assignment 5 (Dashboard Reports — Iowa Liquor Sales). Part of the Master’s in MIS/ML program at the University of Arizona. Includes positive and negative…

    Jupyter Notebook

  4. applied-nlp-assignment-4 applied-nlp-assignment-4 Public

    Applied Natural Language Processing – Assignment 4 (University course). Fine-tuning pre-trained language models (RoBERTa, BART) for SemEval-2020 ComVE subtasks: commonsense validation, multiple cho…

    Jupyter Notebook

  5. final-project-assignment final-project-assignment Public

    Week 6 Final Project for the Master’s in MIS/ML program at the University of Arizona. This project applies a full ML workflow to the German Bank dataset to predict loan defaults, including EDA, pre…

    Jupyter Notebook

  6. vehicle-detection-using-yolov5 vehicle-detection-using-yolov5 Public

    Real-time Vehicle Detection using YOLOv5 — trained on the Vehicles OpenImages dataset for Cars, Trucks, Buses, Motorcycles, and Ambulances. Developed as part of the **Master’s in MIS/ML program at …

    Python