Jie L.

Key Skills

Software

No software listed

Top Subject Matter

LLM response evaluation and bilingual quality assessment (Mandarin Chinese)

AI-assisted code generation evaluation and structured prompt/test-case creation

Legal Services & Contract Review

Top Data Types

Text

Document

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

AI Evaluation & Data Annotation Practice (Independent Practice). Brings 3+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include N, A, and Internal. Education includes N/A, HY Polytechnic College (2026). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

Software Developer / AI Tooling Projects (Freelance / Personal Projects)

Prompt + Response Writing (SFT)

Used AI-assisted development workflows to generate and refine application code and evaluate the resulting technical answers. Built structured prompts and test cases to compare model outputs and detect mistakes in code and technical guidance. Processed structured data artifacts (JSON/CSV/database) derived from these evaluations. • Generated and refined code with AI coding assistants • Assessed technical answers for correctness and usability • Designed prompts/test cases for output comparison • Processed structured evaluation data in JSON/CSV/database formats

2024 - Present

AI Evaluation & Data Annotation Practice (Independent Practice)

Text

Evaluated AI-generated Chinese and English responses for factual accuracy, instruction following, safety, tone, and completeness. Compared multiple model outputs and selected preferred responses based on quality and usefulness for LLM evaluation. Maintained guideline-based consistency across repeated runs. • Rated/corrected response accuracy and completeness • Verified instruction adherence and tone • Ran preference-style comparisons between model outputs • Fed back clear written evaluation notes for improvement

2024 - Present

Education

Work History