About this role
Designs and productizes scalable AI capabilities across a portfolio, turning LLM, agent, and conversational components into reusable services. Establishes integration patterns for RAG, vector search, and model orchestration using Databricks, while standardizing governance, monitoring, and evaluation frameworks.
Key Responsibilities
- Turn models, agents, and conversational interfaces into reusable product capabilities
- Create scalable integration patterns for conversational AI, RAG/vector search, and model orchestration/evaluation
- Standardize AI infrastructure and create shared services/SDKs to reduce time-to-production
- Architect multi-product scale foundations using Databricks (Unity Catalog, Delta Lake, Workflows, Model Serving, Genie)
- Define governance, monitoring, and evaluation frameworks for reliable, secure, production-ready AI
Technical Overview
Builds enterprise AI foundations in Databricks (Unity Catalog, Delta Lake, Workflows, Model Serving, Genie) and implements production AI systems for scalable inference. Develops API-first architectures using Python, REST/GraphQL, and supports vector database and embedding-based retrieval with AI governance and evaluation pipelines.
Ideal Candidate
The ideal candidate is a principal-level AI engineer with 10+ years of experience productizing AI capabilities and deploying production LLM/RAG systems. They have deep Databricks expertise (Unity Catalog, Delta Lake, Workflows, Model Serving, Genie) and strong backend engineering in Python, APIs, microservices, and distributed systems, with proven experience standardizing AI infrastructure and governance frameworks.
Must-Have Skills
10 or more yearsAdvanced AI/ML engineeringincluding large language models (LLMs)RAG architecturesagent frameworksand conversational AI systemsExpertise in the Databricks ecosystem (Unity CatalogDelta LakeWorkflowsModel ServingGenie)Strong backend engineering in Pythonincluding APIsmicroservicesand distributed systems designExperience building and deploying production AI systemsmodel serving pipelinesand scalable inference architecturesProficiency with vector databasesembeddingssemantic searchand retrieval frameworksStrong understanding of cloud-native architectures (AWSAzureor GCP)Bachelors (Required)
Nice-to-Have Skills
Full-stack development experience including ReactNext.jsTypeScriptand modern frontend frameworks for building AI-driven user interfacesExperience designing API-first architecturesREST/GraphQL servicesand AI-enabled application layersExperience building shared platformsSDKsand internal developer toolingKnowledge of data engineering and pipeline patternsincluding ETL/ELT workflows and large-scale data processing
Tools & Platforms
DatabricksUnity CatalogDelta LakeWorkflowsModel ServingGenieReactNext.jsTypeScriptRESTGraphQLAWSAmazon Web ServicesAzureGCPGoogle Cloud PlatformPythonAPIsmicroservicesETL/ELT
Required Skills
DatabricksUnity CatalogDelta LakeWorkflowsModel ServingGenielarge language models (LLMs)RAG architecturesagent frameworksconversational AI systemsvector searchvector databasesembeddingssemantic searchretrieval frameworksmodel orchestrationPythonAPIsmicroservicesdistributed systems designRESTGraphQLAWSAzureGCPETL/ELT workflowsAI governancemonitoringevaluation frameworks
Hard Skills
scalable AI capabilitieslarge language models (LLMs)RAG architecturesagent frameworksconversational AI systemsconversational AIRAG and vector search integrationvector searchmodel orchestrationmodel orchestration and evaluationDatabricksUnity CatalogDeltaWorkflowsModel ServingGenieenterprise-ready AI infrastructureAI governancemonitoringevaluation frameworksAI systems governancesecure AI systemsproduction AI systemsmodel serving pipelinesscalable inference architecturesPythonAPIsmicroservicesdistributed systems designvector databasesembeddingssemantic searchretrieval frameworksReactNext.jsTypeScriptfrontend frameworksAPI-first architecturesRESTGraphQLshared platformsSDKsinternal developer toolingcloud-native architecturesAmazon Web ServicesAWSAzureGoogle Cloud PlatformGCPdata engineeringETL/ELT workflowslarge-scale data processing
Soft Skills
cross-functional collaborationproduct collaborationengineering collaborationdata platform collaborationstandardizing infrastructuredefining governancemonitoringevaluationenabling faster experimentationarchitecture for multi-product scalebuilding shared services and SDKs
Keywords for Your Resume
Principal AI Product EngineerAI Product Engineerlarge language models (LLMs)LLMsRAGRAG architecturesagent frameworksconversational AI systemsconversational AIvector searchvector databasesembeddingssemantic searchretrieval frameworksmodel orchestrationModel ServingDatabricksUnity CatalogDelta LakeWorkflowsGeniePythonmicroservicesdistributed systems designRESTGraphQLAWSAzureGCPETL/ELT workflows
Deal Breakers
Must have 10 or more years of applicable experience, Must have a Bachelor's degree, Must have advanced AI/ML engineering experience with LLMs and RAG, Must have expertise in the Databricks ecosystem (Unity Catalog, Delta Lake, Workflows, Model Serving, Genie)
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile