Olayinka O.

Key Skills

Software

No software listed

Top Subject Matter

LLM engineering for prompt development and evaluation

Top Data Types

Text

Audio

Video

Top Task Types

Classification

Prompt + Response Writing (SFT)

Transcription

Freelancer Overview

Self-Directed AI/LLM Engineering Projects (Prompt engineering and evaluation). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Cursor and ChatGPT. AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Classification.

Labeling Experience

AI/LLM Prompt Engineering Project Lead (Self-Directed) - Self-Directed Projects

TextClassification

You independently designed and tested prompt templates for reasoning, summarization, classification, rewriting, and multi-step workflows. You evaluated model outputs for clarity, tone consistency, accuracy, and task alignment while iteratively improving prompt quality. You documented repeatable instructions and developed small end-to-end simulations using structured evaluation approaches. • Designed and iterated prompt strategies across multiple NLP tasks • Conducted output evaluation for hallucinations, edge cases, and inconsistencies • Implemented system instructions and JSON-mode prompting workflows • Used AI-assisted coding tools to accelerate testing and refinement

2023 - Present

Self-Directed AI/LLM Engineering Projects (Prompt engineering and evaluation)

Text

Self-directed AI/LLM prompt engineering involved generating and testing prompt variations for reasoning, summarization, classification, rewriting, and multi-step workflows. The work included evaluating model outputs for clarity, tone consistency, accuracy, and alignment with task requirements, while identifying failure cases such as hallucinations and edge cases. Results were documented through reusable prompt templates and structured evaluation artifacts. • Designed prompt templates and test cases for repeatability • Performed output evaluation against clarity/tone/accuracy and requirements • Identified hallucinations, inconsistencies, and edge cases to refine prompts • Experimented with chain-of-thought guidance, system instructions, and JSON-mode prompting

2023 - Present

Education

Work History