About this role
Own the evaluation platform for agentic workflows and forecasting pipelines, perform LLM and algorithm evaluation and root-cause analysis on unstructured financial/operational data, curate gold-standard datasets, and build monitoring dashboards and evaluation harnesses to track AI performance for the Applied AI Research team.
Skills for this role
PythonSQLPostgreSQLSnowflakedbtAWSLLM evaluationAgentic workflowsMulti-agent orchestrationTime-series modelsDemand forecastingDataset curationModel monitoringModel drift detectionDashboardingRoot cause analysisLangSmithArize AITruLensStatistical modelingDocument processing