For employers

Hire this AI Trainer

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

Invite to Job
A
Amanuel A.

Amanuel A.

AI Training & Model Alignment Specialist (Technical Data Curation & Adversarial Model Training)

Ethiopia flagAdama, Ethiopia

Key Skills

Software

Label StudioLabel Studio
LabelboxLabelbox
CVATCVAT
Other

Top Subject Matter

Hardware security protocols
technical reasoning
adversarial robustness

Top Data Types

TextText
DocumentDocument
Computer Code ProgrammingComputer Code Programming

Top Task Types

Fine-tuningFine-tuning
RLHFRLHF
Red TeamingRed Teaming
Evaluation/RatingEvaluation/Rating

Freelancer Overview

AI Training & Model Alignment Specialist (Technical Data Curation & Adversarial Model Training). Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Bachelor of Science, Adama Science and Technology University (ASTU) and Certificate, Advent of Cyber (2025). AI-training focus includes data types such as Text and labeling workflows including Fine-tuning, Evaluation, and Rating.

Labeling Experience

Hardware Security Consultant (Remote) / Hardware Security Validation Framework work (security validation supporting AI training/evaluation context)

OtherTextText

Conducted remote security auditing and validation work that included assessing model robustness and effectiveness of security mechanisms in firmware-related contexts. Led threat surface decomposition for complex RTOS-based communication stacks to inform security evaluation outcomes. Although not explicitly framed as data labeling, the role involved structured technical evaluation activities aligned with security-focused AI training preparation.•Security auditing of proprietary firmware relevant to downstream model evaluation•Threat surface decomposition for undocumented RTOS-based communication stacks•Validation of cryptographic countermeasures via controlled fault/glitch testing•Informing security robustness assessments for technical reasoning systems

2023 - 2024

AI Training & Model Alignment Specialist (Technical Data Curation & Adversarial Model Training)

TextTextFine-tuningFine-tuning

Engineered specialized text datasets for technical reasoning and hardware security protocols to improve model accuracy on complex vulnerability assessment tasks. Performed adversarial fine-tuning and red-teaming to strengthen robustness against prompt-injection and logic-based exploits. Built automated reinforcement learning from human feedback (RLHF) pipelines to optimize performance for domain-specific embedded systems queries.•Specialized dataset curation for technical reasoning and hardware security tasks•Adversarial fine-tuning and red-teaming for robustness and exploit resistance•RLHF pipeline development for embedded systems domain optimization•Model alignment efforts for high-complexity vulnerability assessment

2023 - 2024

Education

A

Advent of Cyber

Certificate, Cybersecurity

Certificate
2022 - 2025
A

Adama Science and Technology University (ASTU)

Bachelor of Science, Electronics and Communication Engineering

Bachelor of Science
Not specified

Work History

N

N/A

Hardware Security Consultant

Adama
2023 - 2024
N

N/A

AI Security & Model Alignment Specialist

Adama
2023 - 2024