Opeyemi Bamigbade
Profile

Opeyemi Bamigbade

AI Engineer | PhD Candidate

About Me

I'm an AI Engineer and PhD Candidate specializing in Vision-Language Modeling and high-performance multimodal systems. My work bridges cutting-edge research with real-world deployment by building scalable AI infrastructure, optimizing model performance, and delivering production-ready solutions. I work at the intersection of research and engineering, designing and finetuning multimodal algorithms while architecting systems that run efficiently at scale.

AI Engineering

  • Building Infra-first scalable AI solutions
  • Optimizing performance with fast computing tensors
  • Deploying models at scale with fast inferencing
  • Cloud Architecting with best practices

Research

  • Identifying exact solutions at algorithmic level to complex AI problems
  • Developing modular AI components for easy integration
  • Integration analysis and optimization for performance efficiency

Experience

Senior AI Engineer

Curacel

Dec 2021–2023On-site

Led AI transformation in automobile insurance claims by building and deploying intelligent automation systems. Designed DProcessor, an OCR-based data pipeline that increased claims throughput by 91%, and deployed deep learning object detection models into production. Owned the full MLOps lifecycle, from research to AWS deployment (SageMaker, Lightsail), delivering scalable microservices and a vector search system. Mentored engineers on AI best practices, driving adoption of cloud-native and performance-optimized solutions across the team.

Machine Learning & Backend Engineer

Philanthrolab

Dec 2021–2023Remote

Designed and Optimized Personalization Systems: Engineered AI-driven personalization algorithms using ML and NLP to deliver targeted social/human services and referrals. Developed an NLP model to automatically score user eligibility. Established the core data infrastructure, including user behavior tracking for analytics, database optimization, and robust data wrangling for AI modeling. Delivered full-stack development with flexible backends utilizing REST, GraphQL, and WebSockets.

Machine learning Engineer

Clinify

May 2020–2021Remote

Spearheaded the research and implementation of AI solutions to enhance healthcare software products. Designed and deployed robust Machine Learning system architectures and models for diverse healthcare use cases. Expertise also includes designing technical testing strategies for complex, integrated applications and backend development using NestJS, JavaScript, REST, GraphQL, and WebSockets.

Machine learning Engineer

Data Science Nigeria

June 2019 - 2021Remote

AI/ML Solution research and deployment: Executed diverse projects in NLP and Machine Learning, including developing a CV Ranker and a Conversational Chatbot. Successfully deployed a resource-efficient AI model on edge devices (Raspberry Pi). Applied Deep Learning for facial emotion classification and designed an AI logistics solution for a transportation company (MaxNg). Expertise also includes building microservices for client integration.

Education

PhD in Computer Science (In View)

South East Technology University

2022 – Present Ireland

Research focus on computer vision techniques for indoor scene geolocation, supporting digital forensics and the fight against human trafficking. My work treats colour as a first-class signal, developing colour-augmented representations and embeddings that improve robustness in indoor environments. I also work on attention-driven segmentation methods for image integrity analysis and anomaly scoring, as well as open-set object detection for indoor scene understanding. My broader interests include multimodal AI systems, high-performance computing, and the design of efficient visual–colour pipelines, contrastive architectures, and scalable training systems for real-world investigative applications.

B.Sc. Systems Engineering (First-Class honours)

University of Lagos

2014 – 2018 Nigeria

Final-year research on developing a SaaS platform for automated Gleason score prediction using machine learning, supporting early prostate cancer severity assessment through AI-driven analysis.

  • President, University of Lagos Artificial Intelligence Club
  • Ambassador, Zindi Africa (Data Science Competition Platform equivalent to Kaggle)

Skills

AI Engineering

  • Python | Go
  • PyTorch | TensorFlow | CUDA
  • Scikit-learn | OpenCV | NLTK
  • AWS | GCP | Docker | Kubernetes
  • MCP Servers | FastAPI | Flask
  • MLOps | Git | CI/CD

Research

  • Tensor Operations | Sparse Matrices | Quantization
  • ONNX | TensorRT | TVM
  • VLMs | Attention Mechanisms | Transformers | Diffusion Models
  • Representation Learning | Contrastive Learning
  • Hugging Face | OpenCLIP | DeepSpeed
  • Self-Supervised Learning | Few-Shot Learning

Projects

OpsMate

AI agent-based assistant powered by augmented LLM in a chrome extension using MCP server. Provides a personalized assistant with context-aware conversations login-based persistence, Markdown rendering, and a responsive auto-expanding UI for smooth.

MCP server Augmented LLM Chrome extension OpenAI FastAPI

ML in Containers

Trained, deployed and managed the lifecycle of a vision model in containerized environments, coupled with the inferencing using tensorflow serving. Include a full implementation of CI/CD pipeline using GitHub actions

TensorFlow TensorFlow Serving Docker Swarm FastAPI GitHub Actions

Open Source Contribution: Pylette

Contributing to the easy-to-use Python library for extracting color palettes from images

Python

Open Source Contribution: Tensorflowjs and Danfojs

Contributing to an open source javascript package (danfojs) along with useful illustration on usage with tensorflowjs

TensorFlow

Decision Support System

A Decision Support System for pathologists in the care for prostate cancer. The system leverages deep learning models to analyze histopathological images, providing accurate and efficient diagnostic support.

Keras Streamlit Sklearn Python

ML Model Deployment & Data Pipeline

A project that demystified the building and deployment of custom data pipeline from scratch for a predictive machine learning model

Sklearn Python Github actions FastAPI

Research Publications

Improving Image Embeddings with Colour Features in Indoor Scene Geolocation

Proposed a model architecture that integrates image embeddings with dominant colours and colour histograms across multiple colour spaces. Demonstrated that colour-augmented embeddings significantly improve geolocation accuracy, especially in indoor environments, with classification approaches outperforming deep metric learning methods.

Computer Vision for Multimedia Geolocation: A Systematic Literature Review

Conducted a systematic review of 123 studies on AI and computer vision methods for multimedia geolocation. Highlighted their potential to aid digital forensics, expedite human trafficking investigations, and identified future research directions for enhanced geolocation-based evidence gathering.

Peer Reviewing

I review for leading journals and conferences in Artificial Intelligence, Machine Learning, Computer Vision, and Multimodal Systems. My work includes evaluating research on deep learning architectures, indoor scene Understanding, multimodal modeling, tensor-based techniques, and applied AI systems.

Consultations

Expert Consultation -> tegus.com

Advising startups on Vector search algorithms and databases such as Qdrant, Weaviate, Redis, Milvus, and Elastic

Technical Writing -> mlops.community

Technical writing series on Test-Driven Development in MLOps with code snippets

Expert AI Training Delivering -> Datakirk

Gave series of lectures on Data Science and Machine learning to practitioners and enthusiasts

Blogs

Building Production Machine Learning Systems

How to deploy scalable, production-grade ML systems on Google Cloud with modern MLOps workflows.

Test-Driven Development in MLOps

How to apply TDD to ML workflows to improve reliability, catch data issues early, and build production-ready pipelines.

Connect

Email: bamigbadeopeyemi@gmail.com

LinkedIn: Opeyemi Bamigbade

Twitter: opeyemibami

Github: opeyemibami

Scholar: Opeyemi Bamigbade

Medium: Opeyemi Bamigbade

🗄️ Archive

A collection of past projects, certifications, experiments, and legacy work.