What You’ll Do：
- Analyze assistant interactions, early usage data, and internal evaluations to identify improvement opportunities.
- Generate data-driven insights to guide product development and feature prioritization.
- Conduct research to improve agent architecture and user intent understanding to enhance response quality.
- Design and execute experiments, identifying the right metrics to evaluate impact.
- Collaborate with engineers and other Agent Science team members to implement and productionize improvements.
- Leverage diverse datasets across ecosystem to improve assistant capabilities and deliver customer value.
- Clearly communicate findings and contribute to research and product decisions.

Basic Qualifications：
- 3+ years of experience in data science, machine learning, or a related quantitative field.
- Strong Python skills for data processing, analysis, and prototyping.
- Proficiency in SQL and working with large-scale structured data.
- Solid foundation in statistics, experimental design, and predictive modeling.
- Ability to lead projects end-to-end and work effectively across teams.
- Clear communicator with a proactive, problem-solving mindset.

Preferred Qualifications：
- Experience with conversational AI, NLP, or generative AI systems.
- Familiarity with LLM evaluation methods and user interaction data.
- Background in applied machine learning, cognitive science, or reinforcement learning.
- Experience working in product-oriented, cross-functional environments.