Client Technology - Architecture - Lead Software & AI Architect

At EY, we’re all in to shape your future with confidence.

We’ll help you succeed in a globally connected powerhouse of diverse teams and take your career wherever you want it to go.

Join EY and help to build a better working world.

Fueled by strategic investment in technology and innovation, Client Technology seeks to drive growth opportunities and solve complex business problems for our clients through building a robust platform for business and powerful product engine that are integral to innovation at scale. You will work with technologists and business specialists, blending EY's deep industry knowledge and innovative ideas with our platforms, capabilities, and technical expertise. As a champion for change and growth, you will be at the forefront of integrating emerging technologies from AI to Agentic Solutions, Data Analytics, and next-generation enterprise protocols into every corner of what we do at EY. That means more growth for you, exciting learning opportunities, career choices, and the chance to make a real impact.

The Opportunity

We are looking for a candidate who will be part of the Architecture team within the EY Client Technology's Engineering Architecture Practice. The candidate will be responsible for defining and delivering architectures and designs for business-critical global products and platforms, with focus on scalable distributed systems, cloud-native solutions, modern enterprise architectures, and agentic AI systems. You'll architect solutions hosted in a variety of infrastructure / environments considering reusability, scalability, reliability, observability, and modern design patterns in alignment with EY's mission and strategy. As an architect, you'll embody the principles of the architecture elevator—connecting strategic business vision with hands‑on technical implementation while bridging the gap between executive leadership and engineering teams.

You Will

Build relationships across the business to understand their requirements and strategy, helping them build product / platform roadmaps including agentic AI solutions. Demonstrate architecture leadership to translate business requirements into architecture blueprints and innovative designs incorporating modern distributed systems patterns, microservices architectures, agent orchestration patterns, multi‑agent collaboration frameworks, and cloud‑native solutions.

Own the overall technology, architecture and design landscape of products / platforms from solutioning to delivery to adoption phases, with deep understanding of distributed systems, containerization, orchestration platforms, agent frameworks (LangGraph, Microsoft Agent Framework), agent communication protocols (MCP, A2A), reasoning techniques, and enterprise security patterns.

Design and implement enterprise‑scale distributed and agentic AI solutions using modern protocols and frameworks, with expertise in web APIs (REST, GraphQL), Model Context Protocol (MCP), Agent2Agent Protocol (A2A), containerization with Kubernetes, event‑driven architectures, and robust access control mechanisms using OAuth 2.0 / OpenID Connect, along with AI guardrails using frameworks like NeMo Guardrails, and Guardrails AI.

Potentially lead engineering teams in a portfolio or large product, set the overall technology and architecture direction and own its end‑to‑end delivery in a lead architect's capacity. Act as the critical glue between Engineering, Product Management, AI Safety, and Operations teams, ensuring seamless collaboration and alignment across all stakeholders.

Solve complex problems where scalable solutions may not currently exist, necessitating the ideation and incubation of new distributed system approaches, multi‑agent approaches, advanced reasoning patterns, modern architectural patterns, and cutting‑edge technologies. Conduct technical feasibility assessments, buy / build analysis for platforms, vendor product evaluations, proof of concepts (with hands‑on development) and present various solution options to the business with appropriate recommendations.

Work closely with multi‑disciplinary teams including engineers, AI engineers, prompt engineers, AI safety specialists, data scientists, platform teams, and infosec to deliver modern architectures using optimized delivery approaches, ensuring compliance with enterprise standards, AI governance standards, security policies, and governance guidelines (OWASP GenAI Top 10).

Provide leadership in product delivery to build and consume reusable functional and technical assets. Identify, define and implement reusable components, API libraries, containerized services, agent templates, reasoning patterns, tool integration libraries, evaluation frameworks, and architectural patterns that can be leveraged across the enterprise.

Architect and design distributed systems and multi‑agent systems that can seamlessly interact with multiple enterprise systems, APIs, and data sources while maintaining security through proper authentication implementation and AI safety through guardrail implementation, scalability through containerization and Kubernetes orchestration, and reliability through event‑driven architecture patterns and observability via Open Telemetry evolving AI standards

Provide support to product and project managers in building plans, forecasts, estimations and costs for new products / platforms, including considerations for infrastructure resources, LLM API costs, token usage optimization, containerization costs, and ongoing platform operational requirements.

Provide coaching, mentoring and support to development teams during the delivery phase across the ecosystem, frameworks and platforms. Ensure that developed artifacts comply with envisioned architecture and design, expected quality, security standards, AI safety standards, and recommended development practices through code reviews, prompt reviews, agent workflow validation, and architecture validation processes.

Can work across multiple projects with varied stakeholders, operating as the architecture elevator that connects boardroom strategy with server room implementation. An architect sets architectural direction for scalable systems, builds consensus around technology strategy, mediates conflicts regarding implementation approaches, and provides technical leadership and advisory services while ensuring alignment between Engineering, Product Management, AI Safety, and Operations teams.

Demonstrate excellent interpersonal communication and organizational skills required to operate as a leading member of global, distributed engineering teams. Excel at translating complex technical concepts (including agentic AI concepts) to business stakeholders and business requirements to engineering teams.

Cultivate lasting relationships across business, IT, technology vendors, and industry experts to maintain insight into the broader technology landscape and agentic AI landscape as well as emerging trends. Understand new trends and emerging technologies in multi‑agent systems, reasoning techniques, AI safety, agent protocols, and how they apply to EY's business context.

To Qualify for the Role, You Must Have

Architecture & Leadership

Led and governed global engineering teams and architects, driving the technology and architecture landscape of large and complex portfolios of products / solutions / projects, achieving measurable success in implementation and enterprise adoption. Demonstrated experience as an architecture elevator, connecting strategic business vision with hands‑on technical execution.

Expert‑level proficiency in at least one of the following programming languages : C#, Java, JavaScript, TypeScript, or Python, with demonstrated ability to architect and implement enterprise‑scale solutions including AI‑powered systems using your chosen language stack.

Deep hands‑on experience with modern protocols and frameworks including web APIs (REST, GraphQL), containerization technologies (Docker, Kubernetes), event‑driven architecture patterns, enterprise security implementations using OAuth 2.0 / OpenID Connect, and emerging AI protocols such as Model Context Protocol (MCP) and Agent‑to‑Agent (A2A) communication frameworks. Proven ability to design and implement enterprise‑scale distributed solutions.

Architecture leadership skills with advanced understanding and practical experience in modern architecture patterns, with proven track record in complex, large‑scale implementations serving user bases in the hundreds of thousands or more across the entire product lifecycle. Experience leading engineering teams and acting as the critical connector between Engineering, Product Management, and Operations.

Hands‑on deep experience in architecture including application integration, cloud infrastructure architecture, data pipelines, security architectures, and successful delivery of both functional and non‑functional aspects of platforms using cloud‑native services, full‑stack applications, DevSecOps, security practices, and automated deployment pipelines.

Comprehensive knowledge of modern enterprise technologies including web APIs, microservices architectures, containerization and orchestration platforms (Docker, Kubernetes), event‑driven systems, message queuing, and enterprise security patterns including OAuth 2.0, OpenID Connect, and identity management solutions.

Deep understanding of distributed system architectures, multi‑service systems, API gateway patterns, and the ability to design scalable systems that can handle complex enterprise workloads with proper load balancing, caching strategies, and fault tolerance across enterprise environments.

Expert knowledge of data management including relational and NoSQL databases, data streaming platforms, real‑time data processing, and data governance. Understanding of platform lifecycle management, A / B testing strategies, and performance monitoring.

Strong background in security best practices, enterprise compliance requirements, and regulatory standards in enterprise environments.

Agentic AI & Advanced AI Systems

2+ years of hands‑on experience architecting and implementing enterprise‑scale agentic AI systems, with proven track record in designing and deploying multi‑agent systems and AI orchestration platforms serving significant user bases.

Expert‑level proficiency in major agent frameworks including LangChain / LangGraph (stateful graph‑based agent workflows), Microsoft Ecosystem (AutoGen for multi‑agent systems, Semantic Kernel, migration to Microsoft Agent Framework). Experience with at least 2+ different agent orchestration frameworks in production environments.

Expertise in agent communication protocols and standards : Model Context Protocol (MCP), Agent2Agent Protocol (A2A), AG‑UI event‑based protocols, OpenAPI, JSON‑RPC, Server‑Sent Events (SSE), and WebSockets for agent integration.

Knowledge of advanced reasoning techniques with production implementation experience : ReAct (Reasoning + Acting), Chain‑of‑Thought (CoT), and Tree of Thoughts (ToT). Expert knowledge of planning patterns including Multi‑Plan Selection, External Module‑Aided Planning, Memory‑Augmented Planning, and Task Decomposition.

Hands‑on experience with AI safety frameworks and guardrail implementation : NeMo Guardrails (NVIDIA), Guardrails AI, Azure AI Content Safety or equivalent enterprise platforms. Proven experience implementing multi‑layer guardrail strategies including input guardrails (prompt injection detection, jailbreak prevention, PII masking), output guardrails (hallucination detection, toxicity screening, fact‑checking), runtime guardrails (token‑level monitoring, confidence scoring, circuit breakers), and interaction‑level guardrails (tool use restrictions, decision caps, human‑in‑the‑loop gates).

Experience with LLM evaluation frameworks : DeepEval, RAGAS, LangSmith. Knowledge of evaluation methodologies including LLM‑as‑a‑Judge patterns, Human‑in‑the‑Loop (HITL) annotation and feedback systems, and A / B testing for agent / prompt variants. Deep understanding of key metrics including performance, efficiency, quality, and safety metrics.

Production observability implementation : Span‑level tracking and distributed tracing for multi‑agent systems, cost attribution and token counting, prompt version control, real‑time quality monitoring, and user feedback loops.

Expert‑level skills in RAG (Retrieval‑Augmented Generation) architectures : Agentic RAG, GraphRAG, Multi‑Modal RAG. Production experience with two or more vector databases (MongoDB Atlas Vector Search, Redis, Pinecone, Chroma). Deep understanding of memory architectures for agents including working memory, persistent memory, semantic memory, and episodic memory.

Proven experience designing and implementing multi‑agent systems : Agent coordination mechanisms, inter‑agent messaging, shared knowledge bases, collaborative memory, task delegation and work distribution algorithms. Mastery of orchestration patterns including sequential, concurrent, and hierarchical orchestration, dynamic handoff and context‑based routing, human‑in‑the‑loop integration, and event‑driven agent orchestration.

Cost optimization expertise : Token usage optimization, model selection strategies, and ROI analysis for agentic AI systems.

Demonstrated passion for AI technologies and their potential to transform enterprise solutions, with eagerness to stay current with AI advancements and integrate them thoughtfully into architectural decisions.

Strong background in modern software architecture patterns including event‑driven architectures, data streaming, real‑time processing, and microservices‑based platforms.

Ideally, You'll Also Have

Bachelor's or Master's Degree in Engineering, Computer Science, Data Science, AI / ML, Mathematics, or related technical field.

15+ years overall IT industry experience, and 5+ years in architect roles, including experience with enterprise platform implementations, distributed system deployments, multi‑agent system deployments, and leading cross‑functional engineering teams.

Achieved one or more relevant certifications such as Microsoft Azure Solutions Architect, Microsoft Azure AI Engineer Associate, AWS Solutions Architect, Google Cloud Professional Architect, Google Cloud Professional AI Engineer, TOGAF, Kubernetes certifications (CKA, CKAD), DeepLearning.AI specializations, or emerging distributed systems architecture certifications.

Experience with modern development frameworks and tools such as container orchestration platforms, API management tools, service mesh technologies, or similar distributed systems development ecosystems.

Thought leadership in technology and agentic AI - presenting ideas, products, research papers, and concept papers to varied audiences at AI conferences, building technology points of view and presenting them in industry forums / events, contributing to open‑source projects, and published research on AI.

Experience in designing and implementing business use‑cases using low‑code / no‑code platforms, data reporting, data management and governance technologies, mobile applications, and deep cloud security concepts.

Experience with specialized agentic AI capabilities : Multi‑modal agents (text, vision, audio, video processing), code generation agents (automated programming, code review, bug detection), and domain‑specific agents (finance, healthcare, legal, customer service).

Knowledge of enterprise security including OAuth 2.0 / OpenID Connect implementation, API security, container security, and secure deployment practices.

What We Look For

We want people who are self‑starters with a passion for modern technology innovation and agentic AI innovation, who can take initiative in rapidly evolving technology landscapes and drive digital transformation and AI transformation initiatives. If you can think critically and creatively to solve complex problems using modern distributed systems technologies, multi‑agent systems, advanced reasoning techniques, and enterprise‑grade AI safety frameworks, and can envision how scalable architectures and intelligent agents can transform enterprise operations, you will excel.

You should be comfortable working with culturally diverse teams including engineers, AI engineers, AI safety specialists, platform specialists, data scientists, and offshore development teams, which means you may need to work outside normal hours to collaborate with global engineering teams. Some travel may be required for technology conferences, AI conferences, client implementations, and international project collaboration.

You must demonstrate a deep commitment to AI safety and responsible AI practices, understanding that enterprise agentic AI systems require robust guardrails, continuous monitoring, and adherence to emerging regulatory frameworks. You should be comfortable balancing innovation velocity with safety, governance, and compliance requirements.

What we offer you

The compensation ranges below are provided in order to comply with United States pay transparency laws. Other geographies will follow their local salary guidelines, which may not be a direct conversion of published US salary ranges.At EY, we’ll develop you with future‑focused skills and equip you with world‑class experiences. We’ll empower you in a flexible environment, and fuel you and your extraordinary talents in a diverse and inclusive culture of globally connected teams. Learn more .

We offer a comprehensive compensation and benefits package where you’ll be rewarded based on your performance and recognized for the value you bring to the business. The base salary range for this job in all geographic locations in the US is $138,200 to $266,000. The base salary range for New York City Metro Area, Washington State and California (excluding Sacramento) is $165,800 to $302,300. Individual salaries within those ranges are determined through a wide variety of factors including but not limited to education, experience, knowledge, skills and geography. In addition, our Total Rewards package includes medical and dental coverage, pension and 401(k) plans, and a wide range of paid time off options.

Join us in our team‑led and leader‑enabled hybrid model. Our expectation is for most people in external, client serving roles to work together in person 40‑60% of the time over the course of an engagement, project or year.

Under our flexible vacation policy, you’ll decide how much vacation time you need based on your own personal circumstances. You’ll also be granted time off for designated EY Paid Holidays, Winter / Summer breaks, Personal / Family Care, and other leaves of absence when needed to support your physical, financial, and emotional well‑being.

Are you ready to shape your future with confidence? Apply today.

EY accepts applications for this position on an on‑going basis.

For those living in California, please click here for additional information.

EY focuses on high-ethical standards and integrity among its employees and expects all candidates to demonstrate these qualities.

EY | Building a better working world

EY is building a better working world by creating new value for clients, people, society and the planet, while building trust in capital markets.

Enabled by data, AI and advanced technology, EY teams help clients shape the future with confidence and develop answers for the most pressing issues of today and tomorrow.

EY teams work across a full spectrum of services in assurance, consulting, tax, strategy and transactions. Fueled by sector insights, a globally connected, multi‑disciplinary network and diverse ecosystem partners, EY teams can provide services in more than 150 countries and territories.

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, including arrest and conviction records, in accordance with applicable law.

EY is committed to providing reasonable accommodation to qualified individuals with disabilities including veterans with disabilities. If you have a disability and either need assistance applying online or need to request an accommodation during any part of the application process, please call 1‑800‑EY‑HELP3, select Option 2 for candidate related inquiries, then select Option 1 for candidate queries and finally select Option 2 for candidates with an inquiry which will route you to EY’s Talent Shared Services Team (TSS) or email the TSS at ssc.customersupport@ey.com .

#J-18808-Ljbffr