大模型评测/数据工程师（医疗方向）-小荷健康
Core
Build end-to-end evaluation infrastructure and high-quality medical datasets for large language models in healthcare scenarios like medical Q&A, diagnosis assistance, and imaging understanding.
Role type
Senior IC data engineer (LLM evaluation & data)
Builds
Automated evaluation infrastructure, medical benchmarks, and high-quality training/knowledge datasets
Domain
Healthcare + Large Language Models
Deliverable
production ML models
Required skills
Python/Go/Java/C++, data processing, backend services, task scheduling, LLM fundamentals, RAG, Agent development, automated evaluation, data cleaning, data synthesis, benchmark construction, error analysis
Preferred skills
Medical domain knowledge (clinical guidelines, drug information, medical imaging, EHR), LLM-as-Judge, multi-modal model evaluation
Technologies
Python, Go, Java, C++, RAG, Agent frameworks, LLM-as-Judge
Responsibilities
Develop automated evaluation agents and benchmarks for medical LLMs; construct and manage medical datasets including literature and guidelines; analyze model performance and attribute errors to drive iteration; build data pipelines for training and product optimization
Seniority
Senior, hands-on IC
