For employers

Hire this AI Trainer

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

Invite to Job
L

Laojiang

AI Agent & RAG Engine Developer (AI Data Labeling / Training)

United Kingdom flagCanada Square, Canary Wharf London, E14 5LB United Kingdom, United Kingdom
$18.00/hrIntermediate

Key Skills

Software

No software listed

Top Subject Matter

Enterprise Data
Business Intelligence
Government Digitalization

Top Data Types

TextText
DocumentDocument

Top Task Types

Text Generation
Classification

Freelancer Overview

AI Agent & RAG Engine Developer (AI Data Labeling / Training). Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Engineering, Henan Institute of Technology. AI-training focus includes data types such as Text and Document and labeling workflows including Text Generation and Classification.

IntermediateEnglishChinese MandarinJapanese

Labeling Experience

AI Agent & RAG Engine Developer (AI Data Labeling / Training)

TextText Generation
Developed and maintained autonomous AI agents that leverage local LLMs to generate SQL queries from business text inputs. Led the design of a Document-to-Knowledge retrieval engine focused on high-accuracy semantic search and metadata extraction across various document types. Engineered prompt pipelines for LLM-powered automated text analysis and data verification at enterprise scale. • Implemented highly accurate metadata labeling and extraction workflows leveraging prompt engineering. • Evaluated and refined AI model output for semantic retrieval using local LLM stacks. • Automated production of SQL queries from text prompts to streamline enterprise data analysis. • Orchestrated large-scale, LLM-driven data pipelines for business and technical stakeholders.

Developed and maintained autonomous AI agents that leverage local LLMs to generate SQL queries from business text inputs. Led the design of a Document-to-Knowledge retrieval engine focused on high-accuracy semantic search and metadata extraction across various document types. Engineered prompt pipelines for LLM-powered automated text analysis and data verification at enterprise scale. • Implemented highly accurate metadata labeling and extraction workflows leveraging prompt engineering. • Evaluated and refined AI model output for semantic retrieval using local LLM stacks. • Automated production of SQL queries from text prompts to streamline enterprise data analysis. • Orchestrated large-scale, LLM-driven data pipelines for business and technical stakeholders.

2024 - Present

Automated Document OCR & Metadata Labeling Specialist

DocumentClassification
Deployed and maintained OCR-based document digitization pipelines to automatically extract structured data from large volumes of scanned paper archives. Managed the classification and verification of document types and metadata through automated and semi-automated AI workflows. Facilitated end-to-end, AI-supported annotation and quality monitoring for government digitalization initiatives. • Automated label extraction and validation for over one million legacy documents. • Used AI pipeline outputs to improve labeling accuracy and reduce manual input. • Coordinated large-scale document classification tasks for government data archives. • Monitored and maintained data quality frameworks for continuous annotation improvement.

Deployed and maintained OCR-based document digitization pipelines to automatically extract structured data from large volumes of scanned paper archives. Managed the classification and verification of document types and metadata through automated and semi-automated AI workflows. Facilitated end-to-end, AI-supported annotation and quality monitoring for government digitalization initiatives. • Automated label extraction and validation for over one million legacy documents. • Used AI pipeline outputs to improve labeling accuracy and reduce manual input. • Coordinated large-scale document classification tasks for government data archives. • Monitored and maintained data quality frameworks for continuous annotation improvement.

2021 - 2023

Education

H

Henan Institute of Technology

Bachelor of Engineering, Engineering

Bachelor of Engineering
Not specified

Work History

C

Confidential Entity

AI Solutions Architect & Senior Backend Consultant

N/A
2019 - Present