For employers

Hire this AI Trainer

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

Invite to Job
C
Collins G.

Collins G.

Technical Data Evaluation & Logic Testing (AI model output evaluation and adversarial red-teaming)

Kenya flagNairobi, Kenya

Key Skills

Software

CVATCVAT
LabelboxLabelbox
ProdigyProdigy

Top Subject Matter

AI model safety
logic verification
and hallucination reduction

Top Data Types

TextText
Computer Code ProgrammingComputer Code Programming

Top Task Types

RLHFRLHF
Red TeamingRed Teaming
Text SummarizationText Summarization
Text GenerationText Generation
Fine-tuningFine-tuning

Freelancer Overview

Technical Data Evaluation & Logic Testing (AI model output evaluation and adversarial red-teaming). Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include N, A, and Git and unit testing frameworks. Education includes Bachelor of Science, University of Nairobi (2025). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation, Rating, and Computer Programming.

Labeling Experience

Algorithmic Trading System Developer (logic testing and automated risk validation)

Developed a modular system for automated risk checks within an algorithmic trading pipeline. Implemented circuit breaker logic to enforce strict risk parameters and prevent over-leveraging during volatile conditions. Wrote comprehensive unit tests to ensure logically consistent and zero-error execution under stress. • Validated system behavior against defined risk constraints • Tested edge cases during high-volatility periods • Ensured correctness using structured unit testing • Verified logical consistency of execution paths

2025 - Present

Technical Data Evaluation & Logic Testing (AI model output evaluation and adversarial red-teaming)

TextText

Evaluated AI model outputs for factual accuracy and instruction adherence. Detected and documented logical inconsistencies and hallucinations in generated code and prose. Performed adversarial testing to stress-test reasoning quality in high-stakes scenarios. • Reviewed prompts and responses for compliance with specified instructions • Assessed outputs for grounding and logical validity • Reported hallucination and inconsistency findings • Used adversarial approaches to probe failure modes

2025 - Present

Education

U

University of Nairobi

Bachelor of Science, Computer Science

Bachelor of Science
2025

Work History

T

Technical Data Evaluation & Logic Testing

Technical Data Evaluation & Logic Tester

Nairobi
2024 - 2024
A

Algorithmic Trading System Developer

Algorithmic Trading System Developer

Nairobi
2024 - 2024