Uthman A.

Key Skills

Software

Mercor

OpenCV AI Kit (OAK)

Google Cloud Vertex AI

Top Subject Matter

Agriculture / Computer Vision (farm boundary detection)

Remote sensing / Soil nutrient mapping (CNN-based computer vision)

Top Data Types

Image

Geospatial Tiled Imagery

Computer Code Programming

Top Task Types

Polygon

Classification

Entity (NER) Classification

Bounding Box

Object Detection

Freelancer Overview

Machine Learning Engineer Intern — 2022 RURAL FARMERS HUB (data annotation during collection). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Python. Education includes Master of Science, University of Ibadan (2021) and Bachelor of Science, Federal University of Agriculture, Abeokuta (2015). AI-training focus includes data types such as Geospatial and Tiled Imagery and labeling workflows including Polygon and Classification.

Labeling Experience

Research work as part of dissertation/vision team — Optimizing Deep Neural Networks and classifying plant disease using ConvNets

Classification

Performed satellite imagery preprocessing as part of a computer vision team’s workflow to support training of a convolutional neural network model. The processed imagery was used to map key soil nutrients digitally. This activity involved preparing model-ready inputs derived from geospatial/imagery data. • Preprocessed satellite imagery for downstream modeling • Produced inputs used to train a CNN for nutrient mapping • Supported a computer vision team’s end-to-end data preparation • Enabled creation of digitally mapped soil nutrient outputs

2018 - 2021

Machine Learning Engineer Intern — 2022 RURAL FARMERS HUB (data annotation during collection)

Don't disclosePolygon

Annotated farmland boundaries using geospatial imagery to support an automatic farm boundary detection workflow. The work was performed during the data collection phase to prepare labeled inputs for subsequent modeling. Annotations were created from satellite/geospatial views for use in a computer vision pipeline. • Drew/defined boundary regions for farmland parcels • Used imagery sources from Google Earth during collection • Prepared labeled data for an automatic detection project • Supported downstream computer vision training needs

2020 - 2020

Education

Work History