About this role
Build and maintain production data, feature, and retrieval pipelines that power RAG and ML systems, including ingestion jobs, embedding pipelines, indexing into pgvector, and Celery-based workers. Ship production-quality Python code with tests and observability, collaborate with Data Engineers, Data Scientists, and the Agent/AI squad, and support retrieval, RAG quality, and evaluation workstreams.
Skills for this role
PythonType hintsPydanticpytestRuffMLflowLLMOpsPrompt versioningPortkeyLangChainLlamaIndexModel servingRAGChunking strategiesEmbeddingspgvectorVector storesRe-rankingData ingestionFeature pipelinesCeleryObservabilityMonitoringDockerGitDatabricksAzureAWSExperiment trackingModel registry and promotion workflows (MLflow concepts)