Back to list

Vacancy description

Gen AI GCP Architect - Senior Manager- Bangalore, Gurgaon, Hyderabad in Calcutta, भारत

Ernst & Young

Calcutta, भारत

At EY, you’ll have the chance to build a career as unique as you are, with the global scale, support, inclusive culture and technology to become the best version of you. And we’re counting on your unique voice and perspective to help EY become even better, too. Join us and build an exceptional experience for yourself, and a better working world for all. 

Position: GCP AI Senior Manager

Department: Technology Consulting, D&A       

Title: AI Architect (GenAI)

Educational qualification: BTech/Masters/PhD

Role Overview

We are looking for a Senior Manager – GenAI Architect with 14+ years of experience to own the end‑to‑end solution architecture of enterprise GenAI platforms. This role is heavily focused on solution design, PoC & MVP creation, architectural decision‑making, and production-grade implementation, while guiding teams and stakeholders from idea to scalable delivery.

You will act as the technical authority for GenAI, driving architectural excellence, evaluation strategies, and framework selection across enterprise use cases.

Key Responsibilities

  • Own end‑to‑end GenAI solution architecture, covering ideation, feasibility analysis, PoC execution, MVP design, and production‑ready implementation.
  • Lead solution design and architecture workshops, translating complex business problems into scalable and secure GenAI architectures.
  • Design, implement, and validate PoCs and MVPs to assess technical feasibility, architectural choices, cost-performance trade‑offs, and enterprise fit.
  • Define and standardize enterprise GenAI reference architectures for chatbots, copilots, analytics assistants, and workflow automation use cases.
  • Architect advanced RAG pipelines, including chunking strategies, retrieval methods, embedding optimization, reranking, and grounding techniques.
  • Drive prompt engineering standards across solutions, including system prompt design, instruction tuning, reasoning control, and consistency guidelines.
  • Define and govern prompt evaluation frameworks, covering correctness, faithfulness, hallucination reduction, determinism, latency, cost efficiency, and regression management.
  • Lead architectural decisions around Chain‑of‑Thought (CoT), structured reasoning, and explainability strategies.
  • Architect and review agentic AI systems using LangChain, LangGraph, and custom orchestration layers, including multi‑agent coordination, tool usage, memory, routing, and fallback patterns.
  • Own framework and technology evaluation, selecting appropriate GenAI frameworks based on scalability, reliability, observability, and enterprise constraints.
  • Design scalable and secure FastAPI‑based service architectures to expose GenAI capabilities across enterprise platforms.
  • Define enterprise security architecture, including JWT‑based authentication, authorization, data access controls, and LLM data protection.
  • Lead AWS cloud architecture for GenAI workloads, ensuring scalability, reliability, cost optimization, and secure deployments.
  • Architect and guide usage of DynamoDB, defining access patterns, performance optimization, and cost‑efficient designs.
  • Define vector database architecture, embedding lifecycle management, similarity tuning, and retrieval performance optimization.
  • Own LLM platform and model strategy, including evaluation and usage of AWS Bedrock and Azure OpenAI based on cost, latency, security, compliance, and roadmap alignment.
  • Establish LLMOps practices, including prompt versioning, model versioning, evaluation pipelines, deployment strategies, monitoring, rollback mechanisms, and operational governance.
  • Design observability and evaluation strategies for GenAI systems, covering logging, tracing, prompt metrics, retrieval metrics, agent behavior, and cost monitoring.
  • Define and enforce guardrails and responsible AI practices to minimize hallucinations, prevent data leakage, and ensure compliant and safe GenAI behavior.
  • Review and guide engineering teams through architecture reviews, PoC sign‑offs, MVP readiness, and production certification.
  • Mentor senior engineers, architects, and managers on GenAI architecture, system design, and enterprise delivery best practices.
  • Act as a trusted technical advisor to leadership, providing clarity on feasibility, risks, timelines, and GenAI adoption strategy.

Mandatory Skills

  • 14+ years of experience in software engineering, solution architecture, or AI platform design
  • 5 years of GCP 
  • Strong expertise in Python Object‑Oriented Programming
  • Deep hands‑on experience with RAG architectures, chunking strategies, retrieval optimization, CoT, and guardrails
  • Advanced Prompt Engineering and prompt evaluation methodologies
  • Strong experience with Agentic AI frameworks (LangChain, LangGraph)
  • Expertise in FastAPI and API‑led enterprise architecture
  • Strong AWS architecture experience, including DynamoDB
  • Secure system design using JWT authentication
  • Deep understanding of vector databases and embedding optimization
  • Hands‑on experience with AWS Bedrock and Azure OpenAI
  • Strong knowledge of LLMOps, including evaluation pipelines, deployment, monitoring, versioning, and governance of GenAI systems

Good to Have

  • Experience with enterprise chatbot, copilot, or analytics‑driven GenAI platforms
  • Exposure to compliance‑heavy or regulated enterprise environments
  • Thought leadership in GenAI architecture, governance, or AI platform strategy
  • Experience in Insurance domain

What we are looking for

  • Strong architectural ownership with a builder’s mindset
  • Proven ability to convert ambiguous ideas into working PoCs and MVPs
  • Deep understanding of GenAI reliability, evaluation, and operationalization (LLMOps)
  • Ability to balance innovation, cost, performance, and enterprise risk
  • Strong stakeholder communication and technical influence
  • Vision to scale GenAI solutions from experimentation to enterprise platforms

What we offer

EY Global Delivery Services (GDS) is a dynamic and truly global delivery network. We work across six locations – Argentina, China, India, the Philippines, Poland and the UK – and with teams from all EY service lines, geographies and sectors, playing a vital role in the delivery of the EY growth strategy. From accountants to coders to advisory consultants, we offer a wide variety of fulfilling career opportunities that span all business disciplines. In GDS, you will collaborate with EY teams on exciting projects and work with well-known brands from across the globe. We’ll introduce you to an ever-expanding ecosystem of people, learning, skills and insights that will stay with you throughout your career.

  • Continuous learning: You’ll develop the mindset and skills to navigate whatever comes next.
  • Success as defined by you: We’ll provide the tools and flexibility, so you can make a meaningful impact, your way.
  • Transformative leadership: We’ll give you the insights, coaching and confidence to be the leader the world needs.
  • Diverse and inclusive culture: You’ll be embraced for who you are and empowered to use your voice to help others find theirs.

EY | Building a better working world 

EY exists to build a better working world, helping to create long-term value for clients, people and society and build trust in the capital markets.  

Enabled by data and technology, diverse EY teams in over 150 countries provide trust through assurance and help clients grow, transform and operate.  

Working across assurance, consulting, law, strategy, tax and transactions, EY teams ask better questions to find new answers for the complex issues facing our world today.  

Similar vacancies

More like this role

  • IT
... solutions. The ideal candidate should have exposure to AI/ML systems, backend development, and cloud technologies, with a strong interest in working on real-world GenAI applications. What You’ll Do - Assist in designing and developing GenAI -based applications and services. - Build and maintain backend APIs and microservices ...

Chennai, भारत

  • Hybrid
... pre-trained models and develop custom models for optimal performance and accuracy.- Architect scalable and robust AI platforms on cloud infrastructure (AWS, Azure, GCP) to ensure seamless deployment and operation of Gen AI applications.- Lead the development of APIs and microservices to integrate Gen AI capabilities into existing ...

Pune, भारत

Techwise Digital

AI / GCP Trainer

  • Full-time
  • Contract

Rs 10 - 15 lakhs p.a.

Experience: 4–9 Years Role: AI / GCP Technical Trainer Employment Type: Full-time / Contract Location: [Add Location] Job Summary We are looking for an experienced AI / GCP Trainer to deliver technical training on Artificial Intelligence, Generative AI, Machine Learning and Google Cloud Platform. The ideal candidate should ...

India, भारत

... Experience with Agentic AI, LLM integration, and AI-driven automation is expected. Must Have Skills - Java & Python (Hands-on experience in backend development, AI, and automation workflows using Java and Python) - Microservices Architecture (Experience developing and maintaining scalable microservices) - Spring Boot or Micronaut ...

Bangalore, भारत

  • IT
... integrate robot arms, sensors, cameras, and teleop rigs.- Physical agentic framework: Build agents that turn a job into a plan of steps, execute each one, verify it against real operating procedures, and escalate to a human when unsure. Build in tool use, memory, failure recovery, and human-in-the-loop handoffs.- Cloud planners ...

Bangalore, भारत

  • Hybrid
... Responsibilities - Subject Matter Expertise (SME):- Serve as the hands-on SME for predictive modelling, statistical modelling, Machine Learning, Deep Learning, Generative AI, and Agentic AI solutions.- Architect and review solution design for complex analytics problems across patient journey analytics, HCP/payer/patient ...

Noida, भारत

Yukti Recruitment Solutions

Lead Gen AI Engineer - Python/LLM

  • AI / ML
... RAG pipelines and Agentic AI solutions.- Hands-on experience with LangGraph and/or Google ADK.- Understanding of embeddings, vector databases and retrieval architectures.- Experience working with at least one major cloud platform : AWS, GCP or Azure.- Practical understanding of LLMOps/MLOps, CI/CD and production AI systems.- ...

Hyderabad, भारत

  • Full-time
  • IT
... end-to-end ownership of Generative AI Digital Assistant features — from design and development through to deployment and support. - Develop and maintain Generative AI Digital Assistants using LLMs, AI APIs, and RAG pipelines. - Collaborate with Data Scientists and Software Architects to design and implement intelligent assistant ...

Bangalore, भारत

  • Full-time
  • Research
... prototype and validate new technologies that improve game testing and quality control. This role focuses on building rapid prototypes and running experiments using GenAI, VLMs (Vision-Language Models), and AI/ML to explore automation opportunities across QC. You will work closely with the R&D Manager and cross-functional partners ...

Pune, भारत

KOANTEK INFORMATION SYSTEMS INDIA PRIVATE LIMITED

Koantek - Senior AI Forward Deployed Engineer

  • Remote
  • Data Science
... end-to-end AI/ML project implementations directly with clients.- Design, build, and maintain production-grade AI and ML pipelines, focusing on CI/CD and advanced MLOps/AIOps practices.- Implement and optimize cutting-edge Generative and Agentic AI applications, including multi-agent orchestration and RAG systems.- Architect end-to-end ...

India, भारत