Steve W.

Key Skills

Software

Other

Don't disclose

Top Subject Matter

LLM prompt engineering and custom GPT development for business workflows

LLM evaluation

response ranking

Top Data Types

Text

Document

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

Freelance OpenAI Specialist & Prompt Engineer (Upwork / Remote). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other and Don't disclose. Education includes Bachelor of Science, KCA University (2024). AI-training focus includes data types such as Text and labeling workflows including Prompt + Response Writing (SFT), Evaluation, and Rating.

Labeling Experience

Freelance OpenAI Specialist and Prompt Engineer - Upwork

Text

Designed and optimized complex prompts to improve LLM response accuracy, tone consistency, and formatting adherence for international clients. Built and tested customized OpenAI GPTs tailored to customer support automation, content generation, and technical copywriting needs. Integrated OpenAI APIs into third-party workflows using Zapier and Make.com to streamline operations for e-commerce and digital agency teams. • Prompt engineering and LLM optimization • OpenAI API integration and custom GPT development • Automation workflow implementation with Zapier/Make.com • Independent end-to-end delivery and QA under deadlines.

2025 - Present

Freelance OpenAI Specialist & Prompt Engineer (Upwork / Remote)

OtherTextPrompt + Response Writing (SFT)

Architected and optimized complex prompts to improve LLM response accuracy, tone consistency, and formatting adherence for international clients. Built and tested customized OpenAI GPTs for customer support automation, content generation, and technical copywriting. Integrated OpenAI APIs into third-party automation workflows to streamline AI-driven business operations for e-commerce and digital agency clients. • Designed prompt sets and prompt optimization strategies targeting specific business objectives. • Developed custom GPT configurations and iterated based on evaluation results. • Performed LLM output quality checks to ensure deliverables met required guidelines. • Used automation tooling to connect LLM workflows with operational business systems.

2025 - Present

AI Trainer & LLM Evaluator (Outlier / Remote Platforms)

Don't discloseText

Evaluated and ranked AI-generated responses for multi-turn conversations across accuracy, safety, truthfulness, and helpfulness. Authored high-complexity prompts to stress-test and improve next-generation language models in technical, creative, and logic-based domains. Reworked low-performing outputs and provided justification summaries to support downstream machine learning engineering. • Rated AI responses using criteria focused on quality, safety, and usefulness. • Wrote prompts intended to test model behavior across challenging reasoning and domain scenarios. • Performed correction and rewrite cycles for underperforming generations. • Collaborated with distributed teams to meet data-quality and throughput metrics under shifting schedules.

2024 - Present

Digital Operations & Technical Tasker (Freelance / Nairobi, Kenya)

OtherText

Performed content moderation and quality assurance activities within online business workflows. Ensured outputs complied with project guidelines, SOPs, and quality assurance checklists. Supported ongoing optimization efforts by troubleshooting technical issues affecting content delivery and platform performance. • Reviewed and moderated digital content according to established guidelines. • Checked work against QA checklists to ensure compliance. • Handled data-entry style tasks for operational content pipelines. • Assisted with technical troubleshooting during project sprints.

2023 - 2024

Education

Work History