• Improve existing supervised fraud detection models (primarily XGBoost) through feature engineering, tuning, and evaluation • Design and implement unsupervised and semi-supervised anomaly detection models (e.g., ECOD, Isolation Forest, clustering-based approaches) • Explore ensemble strategies combining anomaly signals, supervised scores, and business rules • Analyze fraud patterns in FNOL (First Notice of Loss) and downstream claim lifecycle data • Develop new model concepts for emerging fraud patterns (temporal anomalies, behavior shifts, structural inconsistencies) • Evaluate bias, stability, and confidence of fraud scores and support threshold calibration • Partner with engineering to productionize models in AWS + Snowflake environments • Support customer-facing analysis and explanations, including Japanese-language discussions when needed • Document findings, assumptions, and tradeoffs clearly for technical and non-technical audiences

• Responsible for designing and managing search recommendation services and models • Knowledge of machine learning powered personalization methods, design patterns and tools • In-depth understanding of Recommendation systems with the business domain knowledge to take the impact of AI product to the next level • Drive the development of core modules with data-driven strategy to maximize the impact • Identify the needs and opportunities, define success metrics with Business and Product management teams

• Data Analysis and Statistical Modeling: Extract valuable insights from large-scale datasets, apply data science methods for statistical analysis and modeling, and transform complex analytical results into clear, actionable visualizations and recommendations to support business decision-making, forecasting, and process optimization. • AI-Driven Initiatives: Lead the design, development, and deployment of LLMs applications/agentic models, collaborating closely with business and technical teams to implement AI solutions that enhance team efficiency and capabilities. • Prompt Engineering and Model Optimization: Utilize prompt engineering, model selection, hyperparameter tuning, model fine-tuning, data retrieval, and coding to develop key product features. Optimize LLM performance to ensure efficient application in business scenarios. • Cross-Functional Collaboration: Work closely with global business and technical teams to gather and analyze requirements, delivering AI and data-driven solutions aligned with strategic objectives.

• Own the full LLM pipeline from data preparation to production real case usage. • Design, iterate and optimize prompts (zero-/few-shot, chain-of-thought, tool-calling, etc.) to maximize model utility and safety across products and languages. • Build and maintain Retrieval-Augmented Generation (RAG) QA/search systems that connect to multi-source knowledge bases. • Familiar with vLLM/SGLang inference architectures and have proven experience deploying and operating LLM services on multi‑GPU or cluster environments. • Design, implement and operate multi‑agent LLM architectures (e.g. LangGraph, CrewAI, AutoGen) including task decomposition, agent orchestration, memory sharing and tool‑calling workflows. • Develop evaluation pipelines (automatic metrics & human feedback) to measure prompt and model quality, bias, and hallucination rates. • Collaborate with product and CS teams to integrate AI models into conversational Chatbot in different scenarios. • Track cutting-edge research, author tech blogs, and keep improve current architecture.