AI Platform Architect

1. Production GenAI experience
2. Vertex AI / Gemini expertise
3. hands-on RAG architecture
4. vector/embedding pipelines

• Lead the design, development, and implementation of scalable, enterprise-grade Generative AI solutions on the Google Cloud Platform, with a strong focus on the Vertex AI suite.
• Architect and build sophisticated Retrieval-Augmented Generation (RAG) systems to ground large language models in HCA’’s proprietary and domain-specific data, ensuring response accuracy and relevance
• Design and implement efficient data pipelines for preparing, processing, and embedding data for use in Vector Stores like Vertex AI Vector Search
• Develop and apply innovative data grounding strategies and design the necessary data structures to connect LLMs with real-world, real-time information sources
• Spearhead the exploration and implementation of Agentic AI concepts to create autonomous systems capable of complex reasoning and task execution.
• Champion and integrate the Model Context Protocol to standardize communication between LLMs and external tools, enhancing system capabilities and interoperability.
• Promote a collaborative team environment and work closely with colleagues to achieve business objectives.
• Collaborate with stakeholders (e.g., business stakeholders, product owners, project managers, and end users) to understand functional and non-functional requirements for AI systems.
• Lead investigations and solution proposals for complex development and design problems in the AI domain.
• Guide team members in the scope of work estimation and forecasting for AI-related projects.
• Perform proof-of-concept and proof-of-technology tasks to secure buy-in from cohorts and stakeholders for new AI initiatives.
• Collaborate with team members to successfully execute development initiatives using Agile practices and principles.

• Bachelor’’s degree Computer Science or related field required.
• 8+ years of experience a Software development or engineering roles required
• Demonstrable experience in delivering Generative AI applications to production in a customer-facing or enterprise environment required

Knowledge, Skills, Abilities, Behaviours Required:

• Growth mindset and a willingness to learn new skills, technologies, and frameworks in the rapidly evolving field of AI
• Advanced knowledge and hands-on experience with Google Cloud Platform Vertex AI, including its generative AI models (e.g., Gemini) and Vertex AI Studio
• Deep understanding and practical experience in designing and building Retrieval-Augmented Generation (RAG) architectures
• Experience with DevOps tooling (e.g., GitHub, Azure DevOps) and CI/CD for machine learning (MLOps)
• Experience with diagramming tools (e.g. Visio)
• Strong Experience in cloud native, deploying within cloud environments, serverless development and/or container-based solutions
• Knowledge of the Model Context Protocol and its application in enabling LLMs to interact with external tools and data preferred
• Familiarity with Agentic AI concepts and frameworks (e.g., LangChain) for building autonomous and multi-agent systems preferred
• Experience interfacing with or working within CRM, ERP, eCommerce, or EMR/EHR solutions and common integration patterns
• Strong Understanding of agile methodology and software development lifecycles preferred
• Demonstrated ability to communicate complex technical information in a condensed manner to various stakeholders verbally and in writing.
• Ability to lead community events with a focus on software development or delivery
• Excellent problem solving and analytical skills
• Ability to sit for long periods of time