Carefull - Data Scientist / AI Engineer

Role overview A senior AI engineering role on the Data team building the detection systems at the heart of a financial safety product focused on protecting older-adult customers. The work spans research into fraud patterns, production-grade detection logic, data enrichment pipelines, and rigorous evaluation of model and pipeline performance.

Responsibilities - Design and ship AI-driven detection features from initial prototype through production deployment - Build data enrichment pipelines that extract structured information from messy, real-world financial transaction data - Research fraud and scam typologies relevant to older adults and translate findings into scalable detection logic - Build reproducible evaluations including test sets, metrics, and error analysis to measure every change - Investigate production or user-reported issues, identify root causes, and ship fixes - Optimize AI pipelines for accuracy, latency, and cost, making informed tradeoffs about model selection and architecture - Partner with customer care, go-to-market, and partner-facing teams to understand real user needs - Track new developments in LLMs and agents and find practical ways to apply them to the product

Requirements - Strong Python skills with experience building data pipelines and production systems - Hands-on experience building LLM applications in production, including prompting, structured outputs, context management, and working with provider SDKs and APIs - Comfort deploying and operating what you build on a cloud platform - A measurement-first habit, with the ability to set up evaluations, read precision and recall, and perform error analysis - Track record of owning work end to end with minimal supervision - Genuine curiosity about how money moves through the US financial system and how scammers exploit it - Comfort reasoning about ambiguity in a domain where answers often depend on context - Clear written and verbal communication in English

Nice to have - AWS experience with Lambda, CDK, Bedrock, Redshift, or DynamoDB - Familiarity with LLM observability and tracing tools such as Langfuse or LangSmith - Background in fraud detection, fintech, or risk and compliance - Experience with financial transaction data including ACH, Zelle, wires, or card payments - Experience working with regulated institutions such as banks - Exposure to elder care, aging-in-place, or financial vulnerability research - Background in data science or ML beyond LLMs, including statistical modeling or anomaly detection