Lead Solution Architect, Customer Analytics, EDW & AI

Position Summary

The Lead Solution Architect Customer Analytics Enterprise Data Warehouse & AI is responsible for establishing enterprise-grade technical architecture that delivers sustained business value across system-wide mission-critical programs. This role owns architectural components and ensures alignment to future-state technology vision directs fit-gap analysis validates migration plans and evaluates technology platforms and architectural patterns to ensure solutions meet rigorous security performance reliability compliance and operability expectations.

This role will focus on customer-facing analytics enterprise data warehouse integrations reporting products APIs dashboards semantic models and AI-enabled data products. The architect will guide full-stack engineering and EDW teams to design scalable secure and reliable platforms that deliver actionable insights to customers through dashboards APIs semantic layers and intelligent AI-powered experiences.

The successful candidate will bring deep experience in data analytics large-scale EDW integrations cloud-native architecture software delivery and enterprise AI solutions including Retrieval-Augmented Generation Agentic AI frameworks LLM orchestration vector search AI APIs and Azure-based AI governance.

Operating with a high degree of autonomy the Lead Solution Architect will consult across multiple domains harmonize initiatives with enterprise architecture set and enforce standards provide clear technical recommendations to non-technical stakeholders and advance measurable outcomes aligned with McKessons strategic objectives.

Key Responsibilities

Enterprise Solution Architecture

• Define and own the target architecture for customer analytics enterprise data warehouse integrations reporting products APIs semantic models dashboards and AI-powered insights.

• Establish architecture standards and reference implementations across Snowflake Databricks data modeling orchestration / ELT APIs front-end consumption and customer-facing AI capabilities.

• Translate business requirements into scalable architecture designs that align with enterprise architecture principles business objectives and technology standards.

• Evaluate technology options platforms and architectural patterns to recommend secure scalable and compliant solution components.

• Lead design reviews and provide architectural direction for high-impact initiatives across data application AI and cloud platforms.

• Ensure solutions meet non-functional requirements for availability performance security observability compliance operability and cost efficiency.

Customer Analytics EDW & Data Platform Architecture

• Lead EDW integration architecture by defining resilient ELT / ETL patterns data contracts lineage quality checks governance controls and measurable service expectations.

• Model data for analytics using facts dimensions semantic layers and data products that support BI tools APIs reporting applications and AI consumption patterns.

• Drive performance tuning partitioning clustering caching and cost governance across storage compute and query layers.

• Design architecture patterns that allow structured and unstructured enterprise data to be securely consumed by AI solutions through governed RAG pipelines.

• Define metadata lineage governance and knowledge-management strategies to improve trust retrieval quality and response grounding.

• Architect semantic layers data products and knowledge graphs that improve contextual retrieval and reasoning across customer analytics platforms.

AI RAG & Agentic AI Architecture

• Define architecture patterns for AI-powered analytics products including conversational analytics natural language query experiences automated insight generation intelligent reporting and autonomous workflow orchestration.

• Design scalable Agentic AI architectures that leverage LLMs multi-agent orchestration frameworks tool calling memory management enterprise APIs and secure execution patterns.

• Establish reference architectures for RAG solutions including document ingestion chunking strategy embedding generation vector search semantic retrieval prompt orchestration grounding and evaluation frameworks.

• Lead integration of enterprise data products with Azure OpenAI Azure AI Foundry Azure AI Search vector databases and external AI APIs.

• Define and promote AI governance practices covering responsible AI model monitoring prompt safety privacy auditability explainability and risk management.

• Establish best practices for prompt engineering model evaluation AI observability retrieval quality measurement agent testing and continuous model improvement.

Engineering Leadership & Delivery Enablement

• Partner with full-stack engineering teams to shape service boundaries API contracts integration patterns and secure data consumption models.

• Guide engineering teams in building AI services copilots intelligent agents and conversational experiences integrated with customer-facing analytics products.

• Create architecture decision records solution diagrams API specifications data contracts standards and knowledge-sharing artifacts.

• Mentor engineers data engineers and architects on architecture patterns secure coding testing reliability logging metrics tracing alerting incident response and operational readiness.

• Drive practical execution from architecture documents to working reference implementations and reusable production-grade patterns.

• Partner across product data governance security customer success engineering and business stakeholders to translate business outcomes into technical roadmaps.

Security Compliance & Governance

• Embed security by design including authentication authorization least privilege encryption secrets management secure APIs and secure data sharing.

• Define controls for secure enterprise data use in GenAI applications including vector stores embeddings prompts LLM interactions model outputs and auditability.

• Support governance for PII / PHI regulatory requirements security controls and audit readiness.

• Lead architecture reviews risk assessments threat modeling and secure-by-default design reviews for data and AI products.

• Ensure solution architecture decisions align with enterprise standards architecture guidelines and governance principles.

Minimum Qualifications

• Bachelors degree in Computer Science Information Systems Engineering or a related field or equivalent experience.

• Typically 10 years of architecture / engineering experience including sustained leadership of enterprise-scale cross-platform programs.

• Experience designing governing and delivering customer-facing analytics reporting or data-product platforms.

• Hands-on experience with large-scale enterprise data warehouse integrations data architecture data modeling ELT / ETL patterns data quality lineage governance and privacy.

• Experience with Snowflake Databricks Spark SQL semantic models data products and analytics platforms.

• Experience with modern service and API design including REST / JSON authentication authorization versioning error handling and secure API consumption.

• Experience designing and deploying Generative AI solutions in enterprise environments.

• Demonstrated experience with RAG architectures including vector databases embeddings document indexing semantic search retrieval orchestration and prompt workflows.

• Practical experience with Agentic AI solutions including multi-agent systems orchestration frameworks tool integration memory patterns reasoning workflows and autonomous task execution.

• Experience with Azure OpenAI Azure AI Foundry Azure AI Search LLM APIs embedding APIs vector databases or related AI services.

• Strong understanding of prompt engineering model evaluation hallucination mitigation guardrails Responsible AI controls and AI application observability.

• Ability to translate complex architecture decisions into clear recommendations for technical and non-technical stakeholders.

• Experience aligning product engineering security data and operations teams to operationalize target architectures and deliver measurable business outcomes.

Preferred Qualifications

• Experience integrating analytics with BI tools such as Power BI Google Looker semantic layers data catalogs and governance tooling.

• Experience with cloud data platforms and services including Snowflake on Azure Databricks Azure Data Factory object storage and event streaming platforms such as Kafka.

• Experience with Azure AI Foundry Azure OpenAI Azure AI Search Microsoft Fabric AI capabilities Semantic Kernel LangChain LangGraph AutoGen CrewAI or similar frameworks.

• Experience implementing vector databases and semantic retrieval platforms such as Azure AI Search Pinecone Weaviate Chroma or equivalent technologies.

• Experience building conversational analytics AI copilots knowledge assistants and intelligent workflow automation solutions.

• Experience with AI evaluation frameworks retrieval quality metrics grounding validation prompt testing safety evaluation and production model monitoring.

• Experience deploying AI applications using containerized and cloud-native architectures on Azure.

• Experience in healthcare IT regulated industries or other large-scale enterprise environments.

Physical Requirements: General Office Demands

Relocation assistance / allowance is not budgeted for this position