EY
Client Technology - Architecture - Lead Software & AI Architect
EY, Washington, District of Columbia, us, 20022
Lead Software & AI Architect
EY Client Technology is looking for a senior architect to define and deliver architectures and designs for business‑critical global products and platforms. The role focuses on scalable distributed systems, cloud‑native solutions, modern enterprise architectures, and agentic AI systems. You will act as the bridge between executive strategy and engineering execution, shaping the technology landscape of EY’s most ambitious initiatives.
Responsibilities
Build relationships across the business to understand requirements and strategy, translate them into architecture blueprints, and develop innovative designs incorporating microservices, agent orchestration, multi‑agent collaboration frameworks, and cloud‑native solutions.
Own the overall technology, architecture, and design landscape of products and platforms from solutioning to delivery and adoption, ensuring reusability, scalability, reliability, observability, and alignment with EY’s strategy.
Design and implement enterprise‑scale distributed and agentic AI solutions using web APIs (REST, GraphQL), Model Context Protocol (MCP), Agent‑to‑Agent Protocol (A2A), Kubernetes, event‑driven architectures, and robust access control (OAuth 2.0/OpenID Connect). Apply AI guardrails with frameworks such as NeMo Guardrails and Guardrails AI.
Lead engineering teams where appropriate, set technology and architecture direction, and ensure seamless collaboration between Engineering, Product Management, AI Safety, and Operations.
Conduct technical feasibility assessments, build B‑A‑B analyses, evaluate vendors, run proof‑of‑concepts, and present solution options to business stakeholders.
Collaborate with multidisciplinary teams—including AI engineers, prompt engineers, AI safety specialists, data scientists, platform teams, and information security—to deliver architectures that comply with enterprise standards and AI governance guidelines.
Develop reusable functional and technical assets, such as API libraries, containerized services, agent templates, and reasoning patterns, for enterprise‑wide use.
Provide coaching and mentoring during the delivery phase, ensuring artifacts meet quality, security, and AI safety standards through code reviews, prompt reviews, and architecture validation.
Manage multiple projects with varied stakeholders, acting as the architecture elevator to connect strategy with implementation and to continue aligning stakeholders.
Communicate complex technical concepts, including agentic AI, to business stakeholders and engineering teams.
Cultivate industry relationships to stay current on multi‑agent systems, reasoning techniques, AI safety, and agent protocols.
Qualifications
Lived experience leading global engineering teams and architects, driving technology integration across large product portfolios and achieving measurable enterprise adoption.
Expert proficiency in at least one of C#, Java, JavaScript, TypeScript, or Python, with proven architecture and implementation of AI‑powered solutions.
Hands‑on experience with modern protocols and frameworks: web APIs, Docker, Kubernetes, event‑driven patterns, OAuth 2.0/OpenID Connect, MCP, and A2A. Demonstrated ability to design and deploy enterprise‑scale distributed solutions.
Leadership experience in modern architecture patterns, partnering with Engineering, Product, and Operations throughout the product lifecycle for large‑scale implementations.
Deep knowledge of application integration, cloud infrastructure architecture, data pipelines, security architectures, and delivery of both functional and non‑functional platform aspects using DevSecOps and automated pipelines.
Comprehensive understanding of enterprise technologies: microservices, containerization, orchestration, messaging, and identity management.
Advanced knowledge of distributed systems, API gateway patterns, and design of scalable systems with load balancing, caching, and fault tolerance.
Expertise in data management, relational and NoSQL databases, real‑time data processing, governance, A/B testing, and performance monitoring.
Strong background in security best practices, compliance, and regulatory standards in enterprise environments.
Agentic AI & Advanced AI Systems
2+ years architecting enterprise‑scale agentic AI systems, including multi‑agent orchestration and deployment at scale.
Proficiency in multiple agent frameworks such as LangChain/LangGraph and Microsoft Agent Framework (AutoGen, Semantic Kernel). Deploy at least two different frameworks in production.
Experience with agent communication protocols (MCP, A2A, AG‑UI, OpenAPI, JSON‑RPC, SSE, WebSockets).
Hands‑on expertise in reasoning techniques: ReAct, Chain‑of‑Thought, Tree‑of‑Thought, multi‑plan selection, external module‑aided planning, and task decomposition.
Implementation of AI safety guardrails via NeMo Guardrails, Guardrails AI, Azure AI Content Safety, or equivalent, covering input, output, runtime, and interaction guardrails.
Experience evaluating LLMs with DeepEval, RAGAS, LangSmith, and setting testing frameworks, including HITL and A/B testing.
Production observability: span‑level tracing, cost attribution, token counting, prompt version control, and real‑time quality monitoring.
RAG expertise: Agentic RAG, GraphRAG, multi‑modal RAG, and use of vector databases such as MongoDB Atlas Vector Search, Redis, Pinecone, and Chroma.
Design of multi‑agent coordination, messaging, knowledge bases, and orchestration patterns, including human‑in‑the‑loop integration.
Token usage optimization, model selection strategies, and ROI analysis for agentic AI systems.
Passion for AI technologies, staying current with industry advances, and integrating them into architectural decisions.
Modern software architecture patterns: event‑driven, streaming, real‑time processing, and microservices.
Ideally You’ll Also Have
Bachelor’s or Master’s degree in Engineering, Computer Science, Data Science, AI/ML, Mathematics, or a related field.
15+ years overall IT experience, with 5+ years in architect roles across large‑scale platforms and multi‑agent deployments.
Relevant certifications such as Microsoft Azure Solutions Architect, AWS Solutions Architect, Google Cloud Professional Architect, TOGAF, CKA/CKAD, or DeepLearning.AI specializations.
Experience with modern development tools: container orchestration, API management, service mesh, and other distributed system ecosystems.
Thought leadership in AI and agentic technology: presentations, papers, and contributions to open‑source or industry forums.
Experience designing business use‑cases with low‑code/no‑code platforms, data governance, and cloud security concepts.
Specialized agentic AI capabilities: multi‑modal agents, code generation agents, and domain‑specific agents (finance, healthcare, legal, customer service).
Knowledge of OAuth 2.0/OpenID Connect, API security, container security, and secure deployment practices.
What We Look For We value self‑starters passionate about cutting‑edge technology and AI innovation. You will solve complex problems using distributed systems, multi‑agent orchestration, advanced reasoning, and robust AI safety. You must balance innovation speed with governance, compliance, and responsible AI practices.
What We Offer You
Competitive total rewards: base salary range $138,200 – $266,000 (U.S.), with higher ranges for the NYC metro area, Washington, and California. Benefits include medical, dental, pension, 401(k), and paid time off.
Hybrid work model: 40–60% in‑office, with flexibility for remote collaboration.
Competitive vacation policy with EY‑Paid Holidays, personal and family care, and other leave options.
EY is an equal‑opportunity employer. EY provides equal employment opportunities to applicants and employees without regard to race, color, religion, age, sex, sexual orientation, gender identity/expression, pregnancy, genetic information, national origin, protected veteran status, disability status, or any other legally protected basis. EY is committed to providing reasonable accommodation to qualified individuals with disabilities. If you need assistance during the application process, call 1‑800‑EY‑HELP3, option 2 for candidate inquiries, or email ssc.customersupport@ey.com.
EY focuses on high‑ethical standards and integrity. All candidates are expected to demonstrate these qualities.
EY | Building a better working world
#J-18808-Ljbffr
Responsibilities
Build relationships across the business to understand requirements and strategy, translate them into architecture blueprints, and develop innovative designs incorporating microservices, agent orchestration, multi‑agent collaboration frameworks, and cloud‑native solutions.
Own the overall technology, architecture, and design landscape of products and platforms from solutioning to delivery and adoption, ensuring reusability, scalability, reliability, observability, and alignment with EY’s strategy.
Design and implement enterprise‑scale distributed and agentic AI solutions using web APIs (REST, GraphQL), Model Context Protocol (MCP), Agent‑to‑Agent Protocol (A2A), Kubernetes, event‑driven architectures, and robust access control (OAuth 2.0/OpenID Connect). Apply AI guardrails with frameworks such as NeMo Guardrails and Guardrails AI.
Lead engineering teams where appropriate, set technology and architecture direction, and ensure seamless collaboration between Engineering, Product Management, AI Safety, and Operations.
Conduct technical feasibility assessments, build B‑A‑B analyses, evaluate vendors, run proof‑of‑concepts, and present solution options to business stakeholders.
Collaborate with multidisciplinary teams—including AI engineers, prompt engineers, AI safety specialists, data scientists, platform teams, and information security—to deliver architectures that comply with enterprise standards and AI governance guidelines.
Develop reusable functional and technical assets, such as API libraries, containerized services, agent templates, and reasoning patterns, for enterprise‑wide use.
Provide coaching and mentoring during the delivery phase, ensuring artifacts meet quality, security, and AI safety standards through code reviews, prompt reviews, and architecture validation.
Manage multiple projects with varied stakeholders, acting as the architecture elevator to connect strategy with implementation and to continue aligning stakeholders.
Communicate complex technical concepts, including agentic AI, to business stakeholders and engineering teams.
Cultivate industry relationships to stay current on multi‑agent systems, reasoning techniques, AI safety, and agent protocols.
Qualifications
Lived experience leading global engineering teams and architects, driving technology integration across large product portfolios and achieving measurable enterprise adoption.
Expert proficiency in at least one of C#, Java, JavaScript, TypeScript, or Python, with proven architecture and implementation of AI‑powered solutions.
Hands‑on experience with modern protocols and frameworks: web APIs, Docker, Kubernetes, event‑driven patterns, OAuth 2.0/OpenID Connect, MCP, and A2A. Demonstrated ability to design and deploy enterprise‑scale distributed solutions.
Leadership experience in modern architecture patterns, partnering with Engineering, Product, and Operations throughout the product lifecycle for large‑scale implementations.
Deep knowledge of application integration, cloud infrastructure architecture, data pipelines, security architectures, and delivery of both functional and non‑functional platform aspects using DevSecOps and automated pipelines.
Comprehensive understanding of enterprise technologies: microservices, containerization, orchestration, messaging, and identity management.
Advanced knowledge of distributed systems, API gateway patterns, and design of scalable systems with load balancing, caching, and fault tolerance.
Expertise in data management, relational and NoSQL databases, real‑time data processing, governance, A/B testing, and performance monitoring.
Strong background in security best practices, compliance, and regulatory standards in enterprise environments.
Agentic AI & Advanced AI Systems
2+ years architecting enterprise‑scale agentic AI systems, including multi‑agent orchestration and deployment at scale.
Proficiency in multiple agent frameworks such as LangChain/LangGraph and Microsoft Agent Framework (AutoGen, Semantic Kernel). Deploy at least two different frameworks in production.
Experience with agent communication protocols (MCP, A2A, AG‑UI, OpenAPI, JSON‑RPC, SSE, WebSockets).
Hands‑on expertise in reasoning techniques: ReAct, Chain‑of‑Thought, Tree‑of‑Thought, multi‑plan selection, external module‑aided planning, and task decomposition.
Implementation of AI safety guardrails via NeMo Guardrails, Guardrails AI, Azure AI Content Safety, or equivalent, covering input, output, runtime, and interaction guardrails.
Experience evaluating LLMs with DeepEval, RAGAS, LangSmith, and setting testing frameworks, including HITL and A/B testing.
Production observability: span‑level tracing, cost attribution, token counting, prompt version control, and real‑time quality monitoring.
RAG expertise: Agentic RAG, GraphRAG, multi‑modal RAG, and use of vector databases such as MongoDB Atlas Vector Search, Redis, Pinecone, and Chroma.
Design of multi‑agent coordination, messaging, knowledge bases, and orchestration patterns, including human‑in‑the‑loop integration.
Token usage optimization, model selection strategies, and ROI analysis for agentic AI systems.
Passion for AI technologies, staying current with industry advances, and integrating them into architectural decisions.
Modern software architecture patterns: event‑driven, streaming, real‑time processing, and microservices.
Ideally You’ll Also Have
Bachelor’s or Master’s degree in Engineering, Computer Science, Data Science, AI/ML, Mathematics, or a related field.
15+ years overall IT experience, with 5+ years in architect roles across large‑scale platforms and multi‑agent deployments.
Relevant certifications such as Microsoft Azure Solutions Architect, AWS Solutions Architect, Google Cloud Professional Architect, TOGAF, CKA/CKAD, or DeepLearning.AI specializations.
Experience with modern development tools: container orchestration, API management, service mesh, and other distributed system ecosystems.
Thought leadership in AI and agentic technology: presentations, papers, and contributions to open‑source or industry forums.
Experience designing business use‑cases with low‑code/no‑code platforms, data governance, and cloud security concepts.
Specialized agentic AI capabilities: multi‑modal agents, code generation agents, and domain‑specific agents (finance, healthcare, legal, customer service).
Knowledge of OAuth 2.0/OpenID Connect, API security, container security, and secure deployment practices.
What We Look For We value self‑starters passionate about cutting‑edge technology and AI innovation. You will solve complex problems using distributed systems, multi‑agent orchestration, advanced reasoning, and robust AI safety. You must balance innovation speed with governance, compliance, and responsible AI practices.
What We Offer You
Competitive total rewards: base salary range $138,200 – $266,000 (U.S.), with higher ranges for the NYC metro area, Washington, and California. Benefits include medical, dental, pension, 401(k), and paid time off.
Hybrid work model: 40–60% in‑office, with flexibility for remote collaboration.
Competitive vacation policy with EY‑Paid Holidays, personal and family care, and other leave options.
EY is an equal‑opportunity employer. EY provides equal employment opportunities to applicants and employees without regard to race, color, religion, age, sex, sexual orientation, gender identity/expression, pregnancy, genetic information, national origin, protected veteran status, disability status, or any other legally protected basis. EY is committed to providing reasonable accommodation to qualified individuals with disabilities. If you need assistance during the application process, call 1‑800‑EY‑HELP3, option 2 for candidate inquiries, or email ssc.customersupport@ey.com.
EY focuses on high‑ethical standards and integrity. All candidates are expected to demonstrate these qualities.
EY | Building a better working world
#J-18808-Ljbffr