For employers

Hire this AI Trainer

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

Invite to Job
F
Faith A.

Faith A.

Researcher (Academic Project) — AI Security Research at Caleb University (LLM prompt-injection defense system)

Nigeria flagLagos, Nigeria

Key Skills

Software

Other
MercorMercor
MindriftMindrift
TolokaToloka

Top Subject Matter

LLM security
prompt injection defense
adversarial prompting

Top Data Types

TextText
Computer Code ProgrammingComputer Code Programming

Top Task Types

Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)
Red TeamingRed Teaming
Computer Programming/CodingComputer Programming/Coding

Freelancer Overview

AI & Data Evaluation (Freelance). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Science, Caleb University. AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Red Teaming.

Labeling Experience

Quality Assurance and Cybersecurity Intern (AI chatbot testing)

OtherTextTextRed TeamingRed Teaming

Tested and secured an AI chatbot system by simulating prompt injection attacks and validating secure data handling practices. Assessed how the system handled adversarial inputs to improve resilience against threats. Documented results to inform security and robustness enhancements for civil society query handling. • Simulated prompt injection and adversarial behaviors • Validated secure data handling and system safeguards • Evaluated chatbot resilience under malicious prompts • Supported robustness improvements for AI safety in deployment

2024 - 2024

AI & Data Evaluation (Freelance)

OtherTextText

Performed AI response evaluations focusing on accuracy, consistency, safety, and contextual relevance. Conducted structured testing using prompt variation and adversarial inputs to identify weaknesses in instruction-following. Logged and analyzed observed failures such as hallucinations and unsafe outputs to support quality improvements. • Evaluated response quality across diverse prompts and contexts • Identified hallucinations, unsafe content, and instruction-following gaps • Reviewed system behavior for safety and contextual alignment • Documented findings from adversarial and robustness tests

2026

Education

C

Caleb University

Bachelor of Science, Cyber Security

Bachelor of Science
Not specified

Work History

F

Freelance

Frontend Developer (Freelance)

N/A
2021 - Present
B

BudgIT

Quality Assurance and Cybersecurity Intern

Lagos
2024 - 2024