Job Summary
We are seeking a hands-on Data Scientist with at least 6 years of experience in data science, specifically focused on Natural Language Processing (NLP). The ideal candidate will have strong Python programming skills and demonstrated experience developing, evaluating, and improving Large Language Model (LLM)-based applications. This role focuses on applied LLM development, prompt engineering, multi-step workflows, Python-based data pipelines, dataset preparation and validation, and systematic evaluation of AI performance. The candidate must be able to build, troubleshoot, and deliver production-ready LLM/NLP solutions rather than focusing solely on prompt writing.
Key Responsibilities
• Develop, evaluate, and improve AI-driven solutions focused on NLP and LLM-based applications.
• Design and implement prompt engineering solutions, including prompt design, structured outputs, and retrieval strategies.
• Develop and maintain Python-based data pipelines.
• Prepare, validate, and manage datasets for AI and NLP applications.
• Design and implement systematic LLM evaluation processes to measure and improve model performance.
• Develop and support multi-step AI workflows.
• Build, troubleshoot, and deliver production-ready LLM/NLP solutions using Python.
• Evaluate AI solution performance and implement improvements based on controlled testing and evaluation results.
Required Qualifications
• Minimum of 6 years of experience in data science, specifically focused on NLP.
• Experience developing LLM-based applications.
• Very strong Python programming skills.
• Demonstrated implementation and delivery experience in prompt engineering, including prompt design, structured outputs, retrieval, and systematic LLM evaluation.
• Relevant education required.
Preferred Qualifications
• Ability to communicate in Mandarin.
• Experience with Retrieval-Augmented Generation (RAG) or agentic systems.
