Nyx V.

Key Skills

Software

Don't disclose

Other

Top Subject Matter

LLM safety

adversarial prompting

RLHF-style evaluation

Top Data Types

Text

Computer Code Programming

Top Task Types

Red Teaming

Question Answering

Freelancer Overview

AI Prompt Engineering & Red Teaming (Self-directed). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Other. Education includes Bachelor of Civil Engineering, Xi'an University of Technology (2025). AI-training focus includes data types such as Text and labeling workflows including Red Teaming, Evaluation, and Rating.

Labeling Experience

AI Prompt Engineering & Red Teaming (Self-directed)

Don't discloseTextRed Teaming

From 2022 to the present, the self-directed role focuses on testing frontier LLMs through adversarial prompt crafting and jailbreak experimentation. The work evaluates model boundary behaviors, safety mechanisms, and response patterns while documenting failure modes such as hallucinations and logical inconsistencies. The goal is to generate human feedback that can support AI safety improvements and alignment training through rigorous red-teaming. • Tested multiple models (ChatGPT, Grok, Claude, Gemini) and AI agents to compare safety behavior • Designed and iterated jailbreak prompts to probe constraints and robustness • Assessed outputs for hallucination likelihood and logical or factual inconsistency • Performed prompt/response evaluation to support adversarial testing and feedback quality

2022 - Present

National College Students Innovation and Entrepreneurship Project Leader

OtherText

Between 2022 and 2024, leadership in a national innovation project included planning and execution responsibilities that supported AI-adjacent experimentation. While the resume does not specify direct labeling artifacts, the project work involved structured evaluation and coordination activities typical of preparing training materials or assessed outputs. The role contributed to maintaining technical quality and logical rigor in an innovation workflow. • Led project planning, team coordination, and execution across 2022–2024 • Applied logical reasoning and problem-solving to advance project deliverables • Supported structured evaluation steps as part of project execution • Managed task completion and process for consistent outcomes

2022 - 2024

One-on-One Teaching / Peer Tutor (University)

TextQuestion Answering

During university tutoring, the work involved one-on-one teaching that supported student learning through explanations and Q&A. Although not framed as data labeling, it is AI-training-adjacent human feedback in the form of guided problem solving for mathematics and physics-related topics. This improved communication of complex concepts through iterative questioning and clarification. • Provided tailored explanations for mathematics and physics concepts • Answered student questions and guided them through step-by-step reasoning • Adapted explanations based on student understanding • Practiced clear, patient feedback delivery for learning outcomes

Not specified

Education

Work History