大模型应用开发工程师LLM Application Engineer
RemoteChina
Job Summary
Integrate and invoke leading LLMs to achieve high-precision structured information extraction, then design and implement semantic parsing pipelines for batch HTML or document processing. Continuously optimize Prompt Engineering templates to improve output accuracy while managing structured results in JSON, CSV, or databases. Build parallel processing architectures with error-retry mechanisms to ensure system stability during large-scale operations, and develop reusable technical scripts for rapid deployment. End-to-end ownership covers data sample design, model fine-tuning, and final output delivery. This remote, part-time role offers flexible hours with milestone-based payments over an initial 2-month project cycle.
Required Qualifications
- Bachelor's degree or higher in Computer Science, AI, or related fields
- 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
- Ability to independently write LLM integration code
- Deep understanding of HTML DOM structures
- Proficiency in text localization and parsing techniques such as CSS Selectors and XPath
- Expertise in OpenAI API
- Expertise in Claude API
- Expertise in LangChain or LlamaIndex frameworks
- Hands-on experience in multi-model integration
- Strong background in data cleaning
- Strong background in semantic extraction
- Strong background in text normalization
- Experience using BeautifulSoup
- Experience using Regex
- Experience using prompt workflow optimization tools
- Proven ability to independently manage the complete workflow from sample preparation and prompt tuning to batch production
- Reliable high-speed internet connection
- Strong commitment to clean code standards
- Strong commitment to version control best practices
- Proficient in English
- Ability to read technical documentation
- Ability to leverage global developer resources to solve complex problems
Desired Qualifications
- Proven track record of deploying LLM applications, especially in automated parsing, Q&A systems, or data extraction
- Familiarity with Serverless architectures such as Cloudflare Workers, Vercel, or AWS Lambda
- In-depth research or strong interest in AI Agents, RAG (Retrieval-Augmented Generation), and knowledge extraction systems
- Experience in LLM fine-tuning
- Experience in inference optimization
- Experience in large-scale distributed system design
- Publications in top-tier conferences (NeurIPS, ICML, ACL)
- Active contributions to open-source communities like Hugging Face
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.