Stephene O.

Key Skills

Software

Other

Top Subject Matter

Financial services domain (banking NLP)

Conversational AI evaluation and LLM safety/reasoning

Academic content writing and structured generation

Top Data Types

Text

Image

Document

Top Task Types

Entity (NER) Classification

RLHF

Prompt + Response Writing (SFT)

Freelancer Overview

Data Service Specialist (Freelance) — RWS Group. Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor’s Degree in Economics, Egerton University. AI-training focus includes data types such as Text and labeling workflows including Entity (NER) Classification, RLHF, and Prompt + Response Writing (SFT).

Labeling Experience

Academic and Content Writer — March 2021–Present

OtherTextPrompt + Response Writing (SFT)

Conducts academic and content writing with strict adherence to client briefs, formatting requirements, and ethical standards. Produces well-structured, coherent content using evidence and data from credible sources. Edits, revises, and proofreads deliverables to improve clarity, grammar, and overall quality. • Content generation and revision aligned to assignment requirements • Use of structured reasoning to ensure coherence and purpose-driven writing • Quality improvement via client/editor feedback incorporation • Ethical, plagiarism-free content creation with attention to detail

2021 - Present

Conversational AI Evaluator & AI Writing Specialist — Freelance

OtherTextRLHF

Designed and evaluated multi-turn, human-like conversations to stress-test Large Language Models across instruction-following, emotional intelligence, consistency, and safety constraints. Acted as a controlled adversary by introducing ambiguity, contradiction, emotional escalation, and shifting user intent to uncover failure modes. Applied RLHF, Direct Preference Optimization (DPO), and Chain-of-Thought (CoT) analysis to assess reasoning depth, coherence, and hallucination risk. • Multi-turn conversation design and evaluation for LLM behavior • Adversarial red-teaming style prompt creation to trigger failures • Preference/feedback-based assessment using RLHF and DPO concepts • CoT reasoning evaluation to measure coherence and hallucination risk

2021 - Present

Data Service Specialist (Freelance) — RWS Group

OtherTextEntity (NER) Classification

Led high-precision annotation for large-scale text, image, and audio datasets supporting global AI systems. Performed financial domain tagging and entity recognition to improve NLP accuracy for banking AI models. Maintained 99%+ accuracy through rigorous QA audits and taxonomy compliance. • Financial domain tagging and entity recognition for banking-related NLP • QA audits and adherence to annotation taxonomy • Sentiment analysis and intent classification annotation work • Bounding-box and multimodal annotation under tight deadlines

2022 - 2025

Education

Work History