• ML model evaluation and production-level experimentation pipelines
• Statistical understanding of the data, analyzing data for deeper insights
• 2+ years of professional experience in Data Science and Machine Learning

Core Responsibilities

• Collaborate directly with technical leads to design evaluation experiments for model performance assessment
• Set up controlled testing environments for LLM-as-judge scenarios
• Analyze experimental outputs and translate findings into clear, actionable insights
• Develop feature engineering approaches to understand dataset characteristics and quality

Required Technical Skills

• Python, statistical analysis, hypothesis testing
• Advanced data manipulation, feature selection, dimensionality reduction
• A/B testing, cross-validation, statistical significance testing
• Understanding of language model evaluation challenges and LLM-asjudge methodologies

Preferred
• Experience with PyTorch/TensorFlow for model analysis
• SQL for data extraction and analysis
• Visualization tools (matplotlib, seaborn, plotly) for results presentation
• Background in NLP evaluation or model interpretability

Interested parties please send your full resume with your current and expected salary to shirley.cho@manpowergrc.hk