About this role
Design and scale the core infrastructure powering large language model applications across Whatnot, including building retrieval/RAG systems, robust LLM evaluation frameworks, and human-in-the-loop feedback pipelines, while enforcing PII controls and enabling production deployment for business surfaces like recommendations, trust & safety, fraud, and seller tooling.
Skills for this role
Large Language Models (LLMs)Retrieval-Augmented Generation (RAG)MCP serversHuman-in-the-loop feedbackLLM evaluationPythonPostgreSQLDynamoDBElasticsearchRedisDataDogGrafanaAWS SageMakerAWS LambdaAWS KinesisAmazon S3Amazon EC2Amazon EKSAmazon ECSApache KafkaFlinkCI/CDProduction systemsScalable system designModel deploymentPII controlsMonitoring and loggingMachine learning systems and algorithms