Cong Pham

Key Skills

Software

Scale AI

Top Subject Matter

AI Alignment

Code Reasoning

Language Model Evaluation

Top Data Types

Text

Computer Code Programming

Top Task Types

RLHF

Freelancer Overview

DSA Expert, Senior Reviewer. Brings 17+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Scale AI. Education includes Master of Computer Science, VNU University of Engineering and Technology (2012) and Bachelor of Science, VNU University of Engineering and Technology (2010). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

DSA Expert, Senior Reviewer

Scale AITextRLHF

As a DSA Expert and Senior Reviewer at Scale AI and DataAnnotationApp, I contributed extensively to reinforcement learning from human feedback (RLHF) and supervised fine-tuning (SFT) projects for advanced AI models. My responsibilities included writing high-quality prompts, evaluating AI responses, providing golden code and test suite, and rating model behaviors. I excelled in crafting evaluation tasks for both single-turn and multi-turn conversations, deeply testing large language models like Opus, Gemini, and Qwen through prompt engineering and rubrics authoring. • Developed and reviewed over 300 DSA-related prompts for AI evaluation • Authored 200+ prompts to test and curate model conversational behaviors • Provided high-quality RLHF and SFT data for model improvement • Rated as an 'excellent reviewer (Oracle)' across multiple projects

As a DSA Expert and Senior Reviewer at Scale AI and DataAnnotationApp, I contributed extensively to reinforcement learning from human feedback (RLHF) and supervised fine-tuning (SFT) projects for advanced AI models. My responsibilities included writing high-quality prompts, evaluating AI responses, providing golden code and test suite, and rating model behaviors. I excelled in crafting evaluation tasks for both single-turn and multi-turn conversations, deeply testing large language models like Opus, Gemini, and Qwen through prompt engineering and rubrics authoring. • Developed and reviewed over 300 DSA-related prompts for AI evaluation • Authored 200+ prompts to test and curate model conversational behaviors • Provided high-quality RLHF and SFT data for model improvement • Rated as an 'excellent reviewer (Oracle)' across multiple projects

2025 - Present

Education

Work History