For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
Shavarie Gordon

Shavarie Gordon

AI Conversational Analyst & Adversarial Tester

JAMAICA flag
Montego bay, Jamaica
$19.00/hrExpertOther

Key Skills

Software

Other

Top Subject Matter

Conversational AI/Natural Language Processing
Conversational AI/Linguistic Analysis

Top Data Types

TextText
ImageImage
AudioAudio

Top Task Types

Red Teaming
Classification

Freelancer Overview

AI Conversational Analyst & Adversarial Tester. Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Arts, University of London (2021). AI-training focus includes data types such as Text and labeling workflows including Red Teaming and Classification.

ExpertEnglish

Labeling Experience

AI Conversational Analyst & Adversarial Tester

OtherTextRed Teaming
I conducted adversarial prompt creation and testing on conversational AI models aimed at identifying hallucinations and safety risks. My work focused on improving model robustness, detecting biases, and strengthening safety policy guardrails. I designed and implemented evaluation scenarios to optimize AI response quality and reliability. • Reduced model's Attack Success Rate (ASR) by 35% through systematic red teaming. • Improved dialogue containment and user experience via custom testing workflows. • Performed NLU testing to refine intent recognition across diverse English dialects. • Collaborated on developing fallback mechanisms for edge-case user interactions.

I conducted adversarial prompt creation and testing on conversational AI models aimed at identifying hallucinations and safety risks. My work focused on improving model robustness, detecting biases, and strengthening safety policy guardrails. I designed and implemented evaluation scenarios to optimize AI response quality and reliability. • Reduced model's Attack Success Rate (ASR) by 35% through systematic red teaming. • Improved dialogue containment and user experience via custom testing workflows. • Performed NLU testing to refine intent recognition across diverse English dialects. • Collaborated on developing fallback mechanisms for edge-case user interactions.

2023 - Present

Narrative Designer / Technical Writer

OtherTextClassification
I performed semantic analysis and linguistic bias identification on large text datasets used for AI model training. My responsibilities included annotating and curating datasets to ensure integrity and removing linguistic biases. I worked on mapping user personas to enhance automated interactions and improve model accuracy. • Conducted analysis on datasets exceeding 50,000 entries for bias detection. • Applied cognitive science principles to labeling processes. • Supported positive sentiment outcomes through improved training data. • Authored documentation supporting annotation and refinement efforts.

I performed semantic analysis and linguistic bias identification on large text datasets used for AI model training. My responsibilities included annotating and curating datasets to ensure integrity and removing linguistic biases. I worked on mapping user personas to enhance automated interactions and improve model accuracy. • Conducted analysis on datasets exceeding 50,000 entries for bias detection. • Applied cognitive science principles to labeling processes. • Supported positive sentiment outcomes through improved training data. • Authored documentation supporting annotation and refinement efforts.

2021 - 2022

Education

U

University of London

Bachelor of Arts, Cognitive Science

Bachelor of Arts
2021 - 2021

Work History

N

Nexus AI Solutions

AI Conversational Analyst & Adversarial Tester

Remote
2023 - Present
L

Lumina Creative Agency

Narrative Designer / Technical Writer

London
2021 - 2022