About this role
Design, build, and iterate on production AI agents and context-layer applications that turn store data into merchant-facing decisions; own models from research to production and build evaluation harnesses to measure recommendation quality and merchant impact (on-site in Flatiron District, New York City).
Skills for this role
Machine LearningLarge Language Models (LLMs)AI AgentsAgent developmentDocument understandingOptical Character Recognition (OCR)Computer VisionEmbeddingsRetrievalRankingpgvectorTypeScriptPythonLangfuseEvalsQA playbooksData analysisModelingOffline testingOnline testingLLM context engineeringLLM observabilityNext.jstRPCPrismaPostgreSQLVercelUser modelingPersonalization