Join EY and forge a career path as unique as you are, leveraging global scale, robust support, and an inclusive culture. We're seeking a Senior Manager – GenAI Architect with over 14 years of experience to spearhead the end-to-end solution architecture for enterprise GenAI platforms.

This pivotal role centers on advanced solution design, crafting Proofs of Concept (PoCs) and Minimum Viable Products (MVPs), making critical architectural decisions, and overseeing production-grade implementations. You will guide teams and stakeholders from initial concept through to scalable delivery, acting as the primary technical authority for Generative AI.

Your responsibilities will include driving architectural excellence, developing evaluation strategies, and selecting appropriate frameworks to meet diverse enterprise use cases. This is an opportunity to shape the future of GenAI within a leading global organization.

Architect end-to-end GenAI solutions, from ideation and feasibility to PoC execution, MVP design, and production-ready implementation. Lead workshops to translate complex business challenges into scalable, secure GenAI architectures. Design, implement, and validate PoCs and MVPs, assessing technical feasibility, architectural choices, and cost-performance trade-offs.

Define enterprise GenAI reference architectures for applications like chatbots, copilots, and analytics assistants. Architect advanced RAG pipelines, optimize chunking strategies, retrieval methods, and embedding techniques. Drive prompt engineering standards, including system prompt design and consistency guidelines. Establish prompt evaluation frameworks covering correctness, hallucination reduction, and latency.

Lead architectural decisions for Chain-of-Thought and explainability. Architect and review agentic AI systems using frameworks like LangChain and LangGraph, managing multi-agent coordination and tool usage. Oversee framework and technology evaluation, ensuring scalability, reliability, and adherence to enterprise constraints. Design secure FastAPI-based service architectures and define enterprise security protocols, including JWT authentication and data access controls.

Lead AWS cloud architecture for GenAI workloads, focusing on scalability, cost optimization, and secure deployments. Architect and guide DynamoDB usage for performance and cost efficiency. Define vector database architecture and manage embedding lifecycle. Own the LLM platform and model strategy, evaluating AWS Bedrock and Azure OpenAI. Establish LLMOps practices for seamless deployment, monitoring, and governance.

Design observability and evaluation strategies for GenAI systems, covering logging, tracing, and prompt/retrieval metrics. Define and enforce guardrails and responsible AI practices to ensure compliant and safe GenAI behavior. Review and guide engineering teams through architecture reviews and production certification. Mentor senior engineers and architects on GenAI architecture and best practices. Act as a trusted technical advisor to leadership.

A minimum of 14 years of experience in software engineering, solution architecture, or AI platform design is essential. 5 years of experience with Google Cloud Platform (GCP) is required. Proficiency in Python Object-Oriented Programming is a must.

Demonstrate deep hands-on experience with RAG architectures, including chunking strategies, retrieval optimization, Chain-of-Thought (CoT), and implementing guardrails. Expertise in advanced prompt engineering and prompt evaluation methodologies is crucial. Strong experience with agentic AI frameworks such as LangChain and LangGraph is required.

Expertise in FastAPI and API-led enterprise architecture is necessary. Strong AWS architecture experience, including practical knowledge of DynamoDB, is expected. Secure system design, particularly using JWT authentication, is a key requirement. A deep understanding of vector databases and embedding optimization is vital.

Hands-on experience with AWS Bedrock and Azure OpenAI is mandatory. Strong knowledge of LLMOps practices, encompassing evaluation pipelines, deployment strategies, monitoring, versioning, and governance of GenAI systems, is required. Candidates should possess a strong architectural ownership with a builder's mindset, proven ability to convert ambiguous ideas into working PoCs and MVPs, and a deep understanding of GenAI reliability, evaluation, and operationalization. The ability to balance innovation, cost, performance, and enterprise risk, coupled with strong stakeholder communication and technical influence, is critical.