For employers

Hire this AI Trainer

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

Invite to Job
A
Anh M.

Anh M.

AI Data Specialist & Content Evaluator (RLHF prompt-response evaluation and alignment)

Vietnam flagHa Noi, Vietnam

Key Skills

Software

No software listed

Top Subject Matter

Generative AI evaluation
RLHF training data
linguistic quality assurance

Top Data Types

TextText
DocumentDocument

Top Task Types

RLHFRLHF

Freelancer Overview

AI Data Specialist & Content Evaluator (RLHF prompt-response evaluation and alignment). Education includes Bachelor of Science, Hanoi University of Science and Technology (HUST) (2027). AI-training focus includes data types such as Text and Document and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

Data Analysis & Quality Control (AI training data readiness through auditing)

DocumentDocument

The experience involves processing and auditing technical datasets to detect anomalies and improve data reliability for analytical and AI-related workflows. It includes checking numeric/physical system metrics for correctness and consistency at fine temporal resolution. It also supports quality control by identifying systemic errors, bias, and inconsistencies in raw datasets. • Audited experimental datasets for metric accuracy (e.g., millisecond-level verification of dynamics). • Calculated and validated results for rotational dynamics and physical system measurements. • Flagged data anomalies, bias, and inconsistency patterns. • Applied structured quality control to optimize overall dataset quality.

2024 - Present

AI Data Specialist & Content Evaluator (RLHF prompt-response evaluation and alignment)

TextTextRLHFRLHF

The experience involves creating and grading prompt-response pairs to support RLHF-style alignment for generative AI in Vietnamese and English. It includes fact-checking and logic verification by validating multi-step reasoning outputs against ground-truth references. It also covers linguistic and contextual alignment to ensure natural phrasing, correct grammar, and appropriate cultural context in chatbot responses. • Graded prompt-response examples for helpfulness, honesty, and harmlessness criteria. • Verified mathematical and logical consistency in complex LLM outputs. • Checked Vietnamese-English translation quality with attention to phrasing and cultural nuances. • Identified inconsistencies and anomalies to improve overall data quality for training/evaluation.

2024 - Present

Education

H

Hanoi University of Science and Technology

Currently studying

Currently studying
Not specified

Work History

C

Company not specified

Logic: Fact-Checking, Data Auditing, Analysis

Location not specified
Not specified