• Designing and building the ML/LLM solution for data ingestion, knowledge extraction, retrieval, and subsequent reasoning. • Creating the datasets, metrics, and pipelines that drive measurable improvements across the system. • Architecting and improving agents for context retrieval, knowledge extraction, and data alignment, which includes prompt engineering, model selection, and inference optimization. • Establishing MLOps practices, including orchestration, observability, and experiment tracking. • Collaborating with the engineering team on system design and with JetBrains Research on the research agenda. • Defining hiring criteria, growing the ML team, and shaping the ML team culture.

• Design and deploy autonomous AI agents capable of multi-step reasoning, tool-use, and self-correction to navigate complex federal benefit policies. • Develop "Guardrail" layers that synchronize probabilistic LLM outputs with rigid business rules, ensuring benefit determinations adhere strictly to legal and regulatory frameworks. • Implement advanced Retrieval-Augmented Generation (RAG) solutions, utilizing layout-aware parsing to extract information from dense manuals/documentation and unstructured data. • Design and evaluate machine learning models that support both data-driven predictions and symbolic/rule-based automation. • Deploy models into cloud environments with a focus on LLM-specific observability (tracing reasoning loops, monitoring for hallucinations, and detecting data drift in logic). • Ensure every AI-driven determination has a clear, human-readable "audit trail" or reasoning chain that justifies the outcome based on source documentation. • Work alongside solution architects and business stakeholders to translate complex health insurance policies into executable AI logic.

- Design, develop, and maintain scalable data pipelines to support ingestion, transformation, and delivery into centralized feature stores, model-training workflows, and real-time inference services. - Build and optimize workflows for extracting, storing, and retrieving semantic representations of unstructured data to enable advanced search and retrieval patterns. - Architect and implement lightweight analytics and dashboarding solutions that deliver natural language query experience and AI-backed insights. - Define and execute processes for managing prompt engineering techniques, orchestration flows, and model fine-tuning routines to power conversational interfaces. - Oversee vector data stores and develop efficient indexing methodologies to support retrieval-augmented generation (RAG) workflows. - Partner with data stakeholders to gather requirements for language-model initiatives and translate into scalable solutions. - Create and maintain comprehensive documentation for all data processes, workflows and model deployment routines. - Should be willing to stay informed and learn emerging methodologies in data engineering, MLOps and LLM operations.

• Design, build, and maintain backend APIs and services supporting credit risk and fraud decisioning • Deploy and operate machine learning models, scorecards, and business rules in production • Own system reliability, performance, and observability for underwriting and fraud services • Debug and resolve production issues affecting decision accuracy or service availability • Partner closely with data scientists to productionize models and ensure safe, repeatable deployments • Improve system architecture to support scalability, fault tolerance, and operational robustness • Implement monitoring and alerting for model behavior, decision outcomes, and system health • Collaborate with Credit Risk Strategy, Risk Modeling, Tech, and Operations teams to translate strategy into live decisions • Develop deep expertise in Katapult’s credit risk and fraud infrastructure