Taiwo A.

Key Skills

Software

Mindrift

Toloka

Don't disclose

Appen

Clickworker

Top Subject Matter

LLM evaluation (prompt/response rating)

Prompt engineering and AI content review

Functional QA and rubric-based evaluation

Top Data Types

Text

Image

Document

Top Task Types

Prompt + Response Writing (SFT)

Data Collection

Transcription

Evaluation/Rating

Text Summarization

Question Answering

Freelancer Overview

LLM Output Evaluation Practice (Mindrift / Toloka). Brings 11+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Mindrift, Toloka, and Don't disclose. Education includes Bachelor of Education, Ekiti State University. AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

LLM Output Evaluation Practice (Mindrift / Toloka)

MindriftText

Completed LLM output evaluation tasks by rating model-generated responses across multiple criteria. Applied RLHF-style feedback frameworks to improve response quality based on prompt context and expected behavior. Ensured consistency by following evaluation rubrics and identifying failure modes such as unsafe, inaccurate, or unhelpful outputs. • Rated responses for accuracy, helpfulness, safety, and tone • Provided RLHF-style feedback aligned to diverse prompt categories • Compared outputs against expected instruction-following and factuality requirements • Followed platform guidelines to maintain annotation consistency and reliability

2024 - Present

Crowdtester — QA & Functional Testing (Contract / Platform-Based)

Completed structured functional testing tasks on QA platforms by evaluating software behavior against acceptance criteria. Reported defects with severity classifications and expected-versus-actual analysis using reproducible steps. Maintained consistent performance by applying platform-specific guidelines accurately under time pressure. • Evaluated behavior against defined acceptance criteria • Wrote detailed bug reports with severity and reproducible steps • Performed expected vs actual outcome analysis with evidence • Sustained consistent pass rates by following uTest Academy guidelines

2023 - Present

TAINOVA — AI Services Freelancer (Independent Contractor)

Don't discloseTextPrompt + Response Writing (SFT)

Delivered prompt engineering and AI content review services for clients using LLM-assisted workflows. Built structured applications that generate consistent outputs from user inputs through careful prompt structuring and output design. Supported model behavior by incorporating input/output understanding and evaluation of generated responses. • Performed prompt engineering and AI content review • Built React-based tools using Anthropic Claude API for structured generation • Developed repeatable prompt and output templates for consistent results • Iterated prompts to improve response reliability and contextual relevance

2023 - Present

Education

Work History