TopTutorJob
11 - 50 employees
Founded 2017
📚 Education
🎯 Recruiter
🤝 B2B
Education • Recruitment • B2B
TopTutorJob is a specialized recruitment agency focusing on connecting international educators with K-12 educational institutions in China. They provide a comprehensive job placement service, offering support from initial application to visa preparation. Their platform allows job seekers to access a wide range of teaching opportunities across various schools, ensuring a personalized experience tailored to the needs of both educators and schools.
大模型应用开发工程师, LLM
Job not on LinkedIn
🕒 June 12
📊 Check your resume score for this job
Improve your chances of getting an interview by checking your resume score before you apply.
TopTutorJob
11 - 50 employees
Founded 2017
📚 Education
🎯 Recruiter
🤝 B2B
Education • Recruitment • B2B
TopTutorJob is a specialized recruitment agency focusing on connecting international educators with K-12 educational institutions in China. They provide a comprehensive job placement service, offering support from initial application to visa preparation. Their platform allows job seekers to access a wide range of teaching opportunities across various schools, ensuring a personalized experience tailored to the needs of both educators and schools.
📋 Description
• Integrate and invoke leading LLMs such as GPT, Claude, Gemini, and Ollama for high-precision structured information extraction based on semantic understanding • Design and implement semantic parsing pipelines for batch HTML/document processing and integrate them with data extraction rule engines • Continuously optimize Prompt Engineering templates through iterative testing to improve model output accuracy and robustness • Manage and store structured results in JSON, CSV, or databases for downstream data analysis and API delivery • Build parallel processing architectures and error-retry mechanisms to ensure high availability, stability, and high throughput • Develop and maintain reusable technical scripts and documentation for rapid deployment and module reuse • Own the complete development lifecycle from data sample design and model fine-tuning/optimization to final output delivery
🎯 Requirements
• Bachelor’s degree or higher in Computer Science, AI, or a related field • 3+ years of experience in LLM application development or algorithmic research • Proficiency in Python or TypeScript • Ability to independently write complex structured data parsing scripts and LLM integration code • Deep understanding of HTML DOM structures • Proficiency with CSS Selectors and XPath • Expertise in OpenAI API and Claude API • Expertise in LangChain or LlamaIndex • Hands-on experience with multi-model integration and switching • Experience in data cleaning, semantic extraction, and text normalization • Proficiency with BeautifulSoup, regular expressions, and prompt workflow optimization tools • Ability to independently manage sample preparation, prompt tuning, and batch production output • Reliable high-speed internet connection • Strong code-quality standards and version-control practices • Proficient in English, including reading technical documentation and using global developer resources • Bonus: experience deploying LLM applications in automated parsing, Q&A systems, or complex data extraction • Bonus: familiarity with Cloudflare Workers, Vercel, or AWS Lambda serverless architectures • Bonus: research or strong interest in AI Agents, RAG, and knowledge extraction systems • Bonus: experience in LLM fine-tuning, inference optimization, or large-scale distributed system design • Preferred: publications in NeurIPS, ICML, or ACL, or active contributions to open-source communities such as Hugging Face
🏖️ Benefits
• Flexible working hours • Remote work • Project-based settlement, paid by phase/milestone • Potential for long-term collaboration for high-quality deliveries • Participation in product release iterations for high-quality deliveries
Apply Now
