Responsibilities
- Develop and maintain AI systems that detect fraud proactively, leveraging large language models and autonomous agent workflows.
- Create and manage RAG pipelines that connect models to internal fraud intelligence and real-time data signals.
- Iterate on prompt engineering and evaluation frameworks to ensure consistent and measurable model outputs.
- Quickly prototype and deploy new AI-driven features from concept to live production environments.
- Investigate and incorporate emerging data sources and model enhancements to improve fraud detection precision.
- Perform thorough testing to validate system reliability, efficiency, and cost-effectiveness.
- Produce clear, accessible documentation for technical systems, prompts, workflows, and research outcomes.
- Work closely with engineering and data analysis teams to meet shared project objectives.
Work Arrangement
Remote (Worldwide) — LA, London, Jakarta, Bengaluru, Beijing, Singapore
