Toluwalemi Oluwadare

Key Skills

Software

Google Cloud Vertex AI

Clickworker

Axiom AI

Appen

AWS SageMaker

Top Subject Matter

LLM-based Video Content Analysis and Captioning

LLM-Driven Educational Content Generation

AI-Powered Social Media Video Content Evaluation

Top Data Types

Text

Image

Video

Top Task Types

Classification

Text Generation

Text Summarization

Data Collection

Object Detection

Freelancer Overview

Senior Backend Engineer — AI Output Evaluation and Prompt Engineering. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Google Cloud Vertex AI. Education includes Master of Business Administration, University of Ibadan (2026) and Bachelor of Science, University of Ibadan (2021). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Senior Backend Engineer — AI Output Evaluation and Prompt Engineering

Text

As Senior Backend Engineer, I integrated large language models (LLMs) and AI APIs into production workflows, directly evaluating AI-generated textual outputs. My work involved assessing the factual accuracy, coherence, and relevance of AI-generated captions and content for a video storyboard generation system. I routinely crafted precise prompts and applied structured evaluation procedures to ensure high-quality outputs and guideline adherence. • Evaluated AI-generated text and captions for factual accuracy and relevance. • Designed and implemented prompt engineering strategies for LLM workflows. • Applied consistent guidelines to assess output quality in production environments. • Used analytical skills to support structured reasoning and documentation.

As Senior Backend Engineer, I integrated large language models (LLMs) and AI APIs into production workflows, directly evaluating AI-generated textual outputs. My work involved assessing the factual accuracy, coherence, and relevance of AI-generated captions and content for a video storyboard generation system. I routinely crafted precise prompts and applied structured evaluation procedures to ensure high-quality outputs and guideline adherence. • Evaluated AI-generated text and captions for factual accuracy and relevance. • Designed and implemented prompt engineering strategies for LLM workflows. • Applied consistent guidelines to assess output quality in production environments. • Used analytical skills to support structured reasoning and documentation.

2024 - 2026

AI Caption Evaluator — Medfluencers Storyboard Generator

Google Cloud Vertex AIText

As part of the Medfluencers Storyboard Generator project, I utilized Google Cloud Vision API and OpenAI to extract, caption, and evaluate text generated from social media video content. My primary focus was on assessing the accuracy and relevance of the AI-generated captions against the corresponding video frames. This role placed strong emphasis on critical analysis and strict adherence to evaluation instructions for output quality. • Leveraged multimodal AI pipelines for content extraction and evaluation. • Evaluated AI-generated captions for relevance and factual correctness. • Applied structured assessment protocols for consistent quality. • Ensured outputs met production standards for social media engagement.

As part of the Medfluencers Storyboard Generator project, I utilized Google Cloud Vision API and OpenAI to extract, caption, and evaluate text generated from social media video content. My primary focus was on assessing the accuracy and relevance of the AI-generated captions against the corresponding video frames. This role placed strong emphasis on critical analysis and strict adherence to evaluation instructions for output quality. • Leveraged multimodal AI pipelines for content extraction and evaluation. • Evaluated AI-generated captions for relevance and factual correctness. • Applied structured assessment protocols for consistent quality. • Ensured outputs met production standards for social media engagement.

2023 - 2023

AI Output Evaluator & Prompt Engineer — PyWhisperer Project

Text

During the development of PyWhisperer, an AI-powered Python learning platform, I focused extensively on prompt engineering and rigorous evaluation of LLM-generated educational materials. My responsibilities included analyzing the coherence, accuracy, and adaptability of AI-generated lessons tailored to learner interests. I continuously validated content for pedagogical effectiveness and guideline consistency. • Engineered prompts for generating targeted educational content. • Evaluated LLM outputs for instructional accuracy and coherence. • Ensured adaptation of AI lessons to individual learner profiles. • Maintained high standards for content quality and pedagogical value.

During the development of PyWhisperer, an AI-powered Python learning platform, I focused extensively on prompt engineering and rigorous evaluation of LLM-generated educational materials. My responsibilities included analyzing the coherence, accuracy, and adaptability of AI-generated lessons tailored to learner interests. I continuously validated content for pedagogical effectiveness and guideline consistency. • Engineered prompts for generating targeted educational content. • Evaluated LLM outputs for instructional accuracy and coherence. • Ensured adaptation of AI lessons to individual learner profiles. • Maintained high standards for content quality and pedagogical value.

2023 - 2023

Education

Work History