Samuel M.

Key Skills

Software

Other

OpenCV AI Kit (OAK)

Top Subject Matter

NLP sentiment analysis and recommender systems (Swahili/English social media)

Agriculture crop disease classification and predictive analytics

Top Data Types

Image

Text

Top Task Types

Fine-tuning

Classification

Freelancer Overview

Junior AI Engineer — DataSpark Technologies (Remote, Kenya). Brings 7+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other and OpenCV AI Kit (OAK). Education includes Bachelor of Science, University of Nairobi (2020). AI-training focus includes data types such as Computer Code, Programming, and Image and labeling workflows including Fine-tuning and Classification.

Labeling Experience

AI Developer — AfriMind AI Solutions (Hybrid, Nairobi)

OpenCV AI Kit (OAK)ImageClassification

Led development of a crop disease classification solution by training CNN-based models on farmer-submitted images to achieve strong real-world accuracy. Implemented MLOps automation for model retraining and versioning to keep the deployed system up to date. Integrated trained AI features into web applications via APIs and cloud services for end-user delivery. • Trained and iterated a CNN-based crop disease classifier using real-world farmer images. • Implemented automated retraining and model versioning using Docker, MLflow, and GitHub Actions. • Deployed the model as an API for mobile-ready access by thousands of users. • Built and supported additional predictive pipelines (e.g., fintech churn) alongside the image model work.

2022 - Present

Junior AI Engineer — DataSpark Technologies (Remote, Kenya)

OtherFine-tuning

Developed NLP sentiment analysis models for Swahili and English social media using NLTK and Transformer-based methods to improve classification performance. Worked on training and evaluation workflows for real-world, messy text inputs with missing values and outliers. Supported downstream recommendation and analytics by preparing model performance metrics for stakeholders. • Built and trained Transformer/NLTK-based sentiment analysis models on Swahili/English social media data. • Performed data cleaning and feature engineering for noisy IoT-derived datasets used in model development. • Contributed to a recommendation engine workflow for an e-commerce platform. • Produced dashboards to communicate model performance metrics to non-technical stakeholders.

2020 - 2021

Education

Work History