For employers

Hire this AI Trainer

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

Invite to Job
吴忒帅

吴忒帅

Campus Social Agent & Mini-Program (Lead Developer) — Data Refinement for agent response patterns

China flag亳州, China

Key Skills

Software

No software listed

Top Subject Matter

Campus social interactions and user intent mapping
Nutrition domain knowledge and safe model responses

Top Data Types

TextText

Top Task Types

Data CollectionData Collection

Freelancer Overview

Campus Social Agent & Mini-Program (Lead Developer) — Data Refinement for agent response patterns. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Food Nutrition and Health, BoZhou University (2029). AI-training focus includes data types such as Text and labeling workflows including Data Collection, Evaluation, and Rating.

Labeling Experience

AI-Driven Nutrition Assistant (Self-initiated) — Data annotation and response evaluation

TextText

Collected and annotated nutritional data to create a knowledge base for a specialized nutrition AI assistant. Evaluated model responses rigorously to verify scientific accuracy and adherence to safety guidelines. Applied testing workflows to ensure the assistant outputs reliable and compliant nutritional advice. • Annotated nutritional data to support domain knowledge retrieval • Conducted response evaluation against scientific correctness criteria • Checked adherence to safety guidelines for nutritional recommendations • Iterated on evaluation results to improve quality and trustworthiness

Present

Campus Social Agent & Mini-Program (Lead Developer) — Data Refinement for agent response patterns

TextTextData CollectionData Collection

Built and curated a specialized dataset of campus social interactions to train an autonomous social agent. Structured the collected examples to improve downstream intent recognition and recommendation quality. Used Python and LLM prompt logic to align training data patterns with safe, campus-appropriate responses. • Curated dataset entries from campus social interaction signals for training • Refined label/structure to strengthen intent recognition accuracy by 25% • Integrated dataset-driven behavior with agent logic and system prompts • Performed dataset preparation to support event matching and social recommendations

Not specified

Education

B

BoZhou University

Bachelor of Food Nutrition and Health, Food Nutrition and Health

Bachelor of Food Nutrition and Health
2025 - 2029

Work History

C

Company not specified

使用codex claude制作程序,编写代码

Location not specified
Not specified