Kwabena Obeng

AI/ML Engineer building scalable intelligence | Computer Vision & NLP Specialist

Accra, Ghana

slyobeng111@gmail.com +233 593 178 619
KO

About

As an AI/ML Engineer and researcher, I specialize in developing scalable machine learning solutions that address critical challenges in healthcare, agriculture, and social impact domains. My work spans computer vision, natural language processing, and IoT integration, with a strong emphasis on deploying production-ready models that drive measurable outcomes.

My research contributions include award-winning solutions in healthcare AI (clinical reasoning, disease outbreak prediction) and agricultural technology (crop disease detection for mobile deployment). I am particularly interested in responsible AI development, with focus on building systems that are accessible, ethical, and beneficial for underserved communities in developing regions.

Currently pursuing advanced research opportunities to further explore the intersection of AI and social good.

Work Experience

Phrontlyne Technologies Limited

Hybrid Oct 2024 - Present

AI/ML Engineer & Software Developer

• Accelerated claims processing by 40% through custom OCR and object detection models integrated into SnapInsure app

• Increased claims validation accuracy by 45% via RAG model using FAISS and LangChain for real-time document analysis

• Built electronic signature model integrated into core application enabling seamless document signing with YoloV8

• Developed claim cause-to-loss validation system using damage detection models to verify reported damages

• Built cost estimator for damaged car parts with instant web scraping for price comparison to accelerate claims processing

• Implemented Ghana Card OCR system for automated identity verification with paddleOCR

• Developed object tracking model for vehicle inspection to prevent fraud during claim uploads

• Built ASR models using OpenAI Whisper and PyAnnote for speech diarization, automatic transcription, and multi-language translation pipelines

• Developed trash classifier model using YOLOv11 for deployment on robotic arm systems

• Built face recognition-based attendance system with anti-spoofing capabilities

• Developed comprehensive investment management module integrated into Phrontlyne ERP system

• Automated critical business processes in Phrontlyne ERP, improving operational efficiency by 30%

• Executed complex data migration projects ensuring seamless system transitions with zero data loss

• Designed and built comprehensive claims analysis reports using JasperStudio for executive decision-making

• Architected interactive Reinsurance Dashboard using Metabase for real-time risk assessment and portfolio monitoring

• Built advanced claims analytics dashboard featuring word clouds for location analysis, loss description insights, and n-grams visualization for cause-of-loss pattern recognition

Python, LangChain, Computer Vision, NLP, FastAPI, Laravel, YOLOv11, OpenAI Whisper, PyAnnote, FAISS, ERPNext

Dev2Win

Remote Nov 2023 - Present

AI/ML Engineer

• Fine-tuned Mistral model for AI mentorship platform, improving interaction quality by 15%

• Developed mentor-mentee matching algorithm using cosine similarity, achieving 30% better matching accuracy

Python, LangChain, Machine Learning, NLP

MeriSkill

Remote Sep 2023 - Oct 2023

Data Analyst Intern

• Developed diabetes prediction models achieving 85% accuracy using diverse patient attributes

• Created interactive Tableau dashboards, improving stakeholder engagement by 25%

Power BI, Python, Machine Learning, Tableau

Research & Competition Achievements

SUA Outsmarting Outbreaks Challenge

🥈 Silver Medal Zindi Africa

Challenge: "Can you turn the tide on waterborne diseases by predicting the next outbreak in Tanzania?"

Developed machine learning models to predict outbreaks of climate-sensitive waterborne diseases (typhoid, amoebiasis, diarrhoea, schistosomiasis, intestinal worms) in Tanzania using comprehensive datasets spanning water sources, sanitation quality, waste management, health facilities, and climate data from 2019-2023.

Impact: Enabling governments and health organizations to implement timely, targeted interventions and optimize resource allocation for vulnerable populations.

Python, Machine Learning, Time Series Analysis, Public Health Analytics, Climate Data Analysis

Ghana Crop Disease Detection Challenge

🥉 Bronze Medal Zindi Africa

Challenge: "Can you build a model for mobile phones to identify diseases on tomatoes, corn, and peppers?"

Built robust machine learning models for accurate prediction of multiple diseases in corn, pepper, and tomato crops, with focus on generalization to unseen diseases and efficient operation on entry-level smartphones used by subsistence farmers in Africa.

Impact: Supporting food security for millions by enabling timely disease detection in crops that form the backbone of Sub-Saharan African agriculture.

Computer Vision, Mobile ML, Edge Computing, Agricultural AI, Disease Classification

Kenya Clinical Reasoning Challenge

🥈 Silver Medal Zindi Africa

Challenge: "Can your model match real clinicians in rural Kenyan healthcare?"

Developed AI models to replicate clinical reasoning of trained healthcare professionals using 400 authentic clinical prompts from diverse Kenyan healthcare settings. Models predict clinician responses across maternal health, child health, and critical care scenarios.

Impact: Supporting frontline healthcare workers in resource-limited settings with AI-assisted clinical decision making.

NLP, Clinical AI, Healthcare Analytics, Small Data ML, Medical Reasoning

Education

Kwame Nkrumah University of Science & Technology

2020 - 2024

BSc. Computer Engineering | GPA: 3.84

Research Interests: Machine Learning, AI in Healthcare, Computer Vision & Robotics, Deep Learning, LLMs & NLP, Scalable AI, AI Ethics

Honors: Provost's List (2020-2023), Multiple Excellent Student Awards

Skills

Python
Machine Learning
Computer Vision
NLP
Deep Learning
LangChain
FastAPI
Laravel
TensorFlow
PyTorch
OpenCV
ERPNext
Tableau
Metabase
Jasper Reports
SQL
Docker
Git
AWS
MLOps

Featured Projects

QueryAmie queryamie.com

Advanced multilingual document analysis platform supporting 160+ languages with comprehensive agentic capabilities. Features include natural language document interaction, voice chat, web search agents, custom data visualization and regression analysis, research assistant agents, and CV analysis tools.

Key Features: Document upload and analysis, voice-enabled queries, intelligent web search, automated data visualization, custom regression modeling for dataset analysis, research assistance with citation management, and comprehensive CV/resume analysis.

Production App
Python, LangChain, NLP, FastAPI, Voice Recognition, Agentic AI, Data Visualization, Regression Analysis

Jobfit AI jobfit-ai.vercel.app

Intelligent recruitment platform providing personalized job-fit assessments and candidate matching using advanced ML algorithms.

Production App
Machine Learning, NLP, React, Python

Aquamind github.com

IoT-enabled water quality prediction system using LSTM and Gradient Boosting Models, achieving 96% accuracy for real-time monitoring.

Research Project
IoT, LSTM, FastAPI, Arduino, ESP32

British Airways Analytics github.com

Comprehensive customer sentiment analysis and booking prediction system for British Airways. Analyzed customer sentiments, booking patterns, and developed predictive models to enhance customer satisfaction and optimize booking processes.

Simulation Project
Python, Machine Learning, Sentiment Analysis, Predictive Modeling

Image Classification github.com

Convolutional Neural Network built with TensorFlow for multi-class image recognition with data augmentation and transfer learning.

ML Project
TensorFlow, CNN, Computer Vision, Python

Sales Analytics github.com

Comprehensive business intelligence analysis uncovering sales patterns and customer insights using statistical modeling.

Analytics
Python, R, Pandas, Statistical Analysis

Weather Forecasting github.com

Climate data exploration and predictive modeling for weather pattern analysis and forecasting.

Data Science
Time Series, Python, Machine Learning

Mobility Analytics github.com

Uber data analysis revealing mobility patterns and optimizing transportation efficiency through geospatial analytics.

Analytics
Python, Geospatial Analysis, Visualization

Credit Risk Model github.com

End-to-end machine learning pipeline for loan default prediction using ensemble methods and feature engineering.

ML Pipeline
XGBoost, Feature Engineering, Python