For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
S
Shiloh Oni

Shiloh Oni

Independent Researcher (ML Collective) — Fine-Tuning Multilingual Embedding Models

Nigeria flagRemote, Nigeria
$20.00/hrExpertAws SagemakerData Annotation TechDataloop

Key Skills

Software

AWS SageMakerAWS SageMaker
Data Annotation TechData Annotation Tech
DataloopDataloop
Google Cloud Vertex AIGoogle Cloud Vertex AI
OpenCV AI Kit (OAK)OpenCV AI Kit (OAK)

Top Subject Matter

Multilingual NLP
Information Retrieval
Low Resource Speech and Language Technologies

Top Data Types

TextText
ImageImage
VideoVideo

Top Task Types

Fine-tuningFine-tuning
ClassificationClassification
TranscriptionTranscription
Data CollectionData Collection
Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)
Text GenerationText Generation
Question AnsweringQuestion Answering
Computer Programming/CodingComputer Programming/Coding

Freelancer Overview

Independent Researcher (ML Collective) — Fine-Tuning Multilingual Embedding Models. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include PyTorch and Python. Education includes Doctor of Veterinary Medicine, Federal University of Agriculture, Abeokuta (2024). AI-training focus includes data types such as Text and Image and labeling workflows including Fine-tuning and Classification.

ExpertEnglishYoruba

Labeling Experience

Independent Researcher (ML Collective) — Medical Image Classification Labeling

ImageClassification
During my tenure as an Independent Researcher at ML Collective, I built a few-shot learning model to classify various diseases from limited blood smear image data. I labeled and prepared datasets to enable robust disease diagnosis models in medical imaging. My responsibilities involved close attention to image classification accuracy and effective data structuring. • Labeled blood smear images for multi-disease classification training purposes. • Prepared and cleaned medical image datasets for model input. • Evaluated image-based diagnosis models using annotated data. • Enhanced dataset balance and class distributions through careful labeling.

During my tenure as an Independent Researcher at ML Collective, I built a few-shot learning model to classify various diseases from limited blood smear image data. I labeled and prepared datasets to enable robust disease diagnosis models in medical imaging. My responsibilities involved close attention to image classification accuracy and effective data structuring. • Labeled blood smear images for multi-disease classification training purposes. • Prepared and cleaned medical image datasets for model input. • Evaluated image-based diagnosis models using annotated data. • Enhanced dataset balance and class distributions through careful labeling.

2023 - Present

Independent Researcher (ML Collective) — Fine-Tuning Multilingual Embedding Models

TextFine Tuning
As an Independent Researcher at ML Collective, I fine-tuned the BGE-M3 dense embedding model on three Nigerian languages for information retrieval tasks. The work involved curating and annotating text data from local Nigerian documents to enhance multilingual model performance. I contributed to model evaluation and actively participated in discussions reviewing labeling approaches and outcomes. • Fine-tuned embedding models using annotated multilingual textual datasets. • Performed model evaluation on labeled language datasets for accuracy improvement. • Curated and labeled data to boost information retrieval in Nigerian languages. • Participated in team training sessions and discussions on annotation practices.

As an Independent Researcher at ML Collective, I fine-tuned the BGE-M3 dense embedding model on three Nigerian languages for information retrieval tasks. The work involved curating and annotating text data from local Nigerian documents to enhance multilingual model performance. I contributed to model evaluation and actively participated in discussions reviewing labeling approaches and outcomes. • Fine-tuned embedding models using annotated multilingual textual datasets. • Performed model evaluation on labeled language datasets for accuracy improvement. • Curated and labeled data to boost information retrieval in Nigerian languages. • Participated in team training sessions and discussions on annotation practices.

2023 - Present

Education

F

Federal University of Agriculture, Abeokuta

Doctor of Veterinary Medicine, Veterinary Medicine

Doctor of Veterinary Medicine
2017 - 2024

Work History

M

ML Collective

Independent Researcher

Remote
2023 - Present
S

SeqHub Analytics

Data Science Intern

Remote
2024 - 2024