Ediomi I.

Key Skills

Software

Mercor

Clickworker

Data Annotation Tech

Top Subject Matter

Cybersecurity benchmark evaluation and AI safety (LLM output assessment, RLHF feedback)

Cybersecurity benchmarking and security evaluation (training materials supporting AI safety/evaluation)

Legal Services & Contract Review

Top Data Types

Text

Document

Top Task Types

Red Teaming

Text Generation

Data Collection

Prompt + Response Writing (SFT)

Text Summarization

Question Answering

Freelancer Overview

Cybersecurity Benchmark Specialist / AI Safety Evaluator — Mercor as invisible agency. Brings 4+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Mercor, N, and A. Education includes Bachelor of Arts, University Of Uyo (2025) and Certified Information Systems Security Professional, (CISSP) (2026). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Red Teaming.

Labeling Experience

Senior Cybersecurity Analyst — Brooks and Rolls limited

TextRed Teaming

Designed and implemented security benchmarks and control frameworks aligned with recognized industry standards while supporting AI-enhanced security evaluation efforts. Created training materials for emerging threats and AI-enabled security tools to improve team readiness and evaluation capability. Produced or supported benchmark content intended for evaluating and validating cybersecurity behaviors and outputs. • Aligned security benchmarks and controls with NIST and ISO 27001 requirements • Mentored junior analysts and contributed training materials related to emerging threats • Supported benchmarking activities that inform AI evaluation and security testing • Contributed domain guidance used to assess threats and vulnerabilities in evaluated outputs

2022 - 2024

Cybersecurity Benchmark Specialist / AI Safety Evaluator — Mercor as invisible agency

MercorText

Performed in-depth benchmarking and red-team evaluations of AI model outputs for cybersecurity scenarios, identifying jailbreaks, factual errors, and policy violations. Developed and applied evaluation rubrics to consistently assess model performance on penetration testing, vulnerability management, and risk mitigation topics to improve training dataset quality. Collaborated on RLHF feedback cycles by providing expert guidance to strengthen cybersecurity reasoning and safety alignment. • Evaluated incident response, threat intelligence, and secure architecture responses for accuracy and compliance • Scored outputs using rubric-based assessment to generate higher-quality training signals • Provided expert RLHF feedback focused on safety and correctness in cybersecurity domains • Improved dataset quality by flagging unsafe, incorrect, or noncompliant model generations

2023

Education

Work History