For employers

Hire this AI Trainer

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

Invite to Job
Nahmaninov Ben David

Nahmaninov Ben David

AI Data Specialist - Safety & Annotation

Israel flagEilat, Israel
$30.00/hrExpertAppenLabelboxScale AI

Key Skills

Software

AppenAppen
LabelboxLabelbox
Scale AIScale AI
TelusTelus
Other

Top Subject Matter

No subject matter listed

Top Data Types

AudioAudio
DocumentDocument
ImageImage
TextText
VideoVideo

Top Task Types

Audio Recording
Classification
Evaluation Rating
Fine Tuning
Prompt Response Writing SFT
Question Answering
Red Teaming
RLHF
Text Generation
Text Summarization
Transcription
Translation Localization

Freelancer Overview

I am an AI Data Specialist with a strong focus on RLHF and training Large Language Models (LLMs) to be accurate, helpful, and culturally aware. My core experience lies in creating high-quality training data and ranking model outputs in both English and Hebrew, ensuring they strictly follow instructions while maintaining natural linguistic flow. I excel at the nuances of language training, verifying that translations, tone, and cultural contexts are handled correctly to improve model fluency. Beyond standard training, I specialize in Red Teaming and safety evaluation. I design adversarial scenarios ("jailbreaks") to stress-test models and identify safety failures, specifically targeting edge cases where standard guardrails might be bypassed. While my primary expertise is in linguistics and safety, I also leverage a solid technical foundation in STEM to verify logical reasoning chains and factual accuracy when necessary.

ExpertHebrewEnglishJapanese

Labeling Experience

Multilingual RLHF & Red Teaming for Generative AI

Don T DiscloseTextTranslation LocalizationRLHF
extensive experience in RLHF (Reinforcement Learning from Human Feedback) and Red Teaming for advanced Large Language Models. Key Responsibilities: Red Teaming & Safety: Designed adversarial "jailbreak" prompts to stress-test model guardrails, specifically targeting edge cases in safety guidelines and harmful content policies. SFT & Creative Writing: Authored high-quality prompts and responses (Supervised Fine-Tuning) in both English and Hebrew, ensuring natural linguistic flow and cultural accuracy. Technical Evaluation: Evaluated model outputs for logical reasoning and accuracy in STEM subjects (Math/Physics), assessing Chain of Thought (CoT) capabilities. Pipeline Improvement: Provided structural feedback to engineering teams regarding annotation tools and guideline ambiguities to streamline the data pipeline.

extensive experience in RLHF (Reinforcement Learning from Human Feedback) and Red Teaming for advanced Large Language Models. Key Responsibilities: Red Teaming & Safety: Designed adversarial "jailbreak" prompts to stress-test model guardrails, specifically targeting edge cases in safety guidelines and harmful content policies. SFT & Creative Writing: Authored high-quality prompts and responses (Supervised Fine-Tuning) in both English and Hebrew, ensuring natural linguistic flow and cultural accuracy. Technical Evaluation: Evaluated model outputs for logical reasoning and accuracy in STEM subjects (Math/Physics), assessing Chain of Thought (CoT) capabilities. Pipeline Improvement: Provided structural feedback to engineering teams regarding annotation tools and guideline ambiguities to streamline the data pipeline.

2023

Education

T

Technion - Israel Institute of Technology

Pre-Academic Intensive Science Program Certificate, Science

Pre-Academic Intensive Science Program Certificate
2022 - 2022

Work History

F

Fixit

Technical Support & Customer Success

Eilat
2022 - 2023
I

Israel Defense Forces

Networking & Computer Technician

Israel
2020 - 2022