EY
EY

EY is a global professional services firm offering audit, tax, consulting, and advisory expertise. Its teams help organizations address complex business challenges, strengthen trust in financial reporting and markets, and use data and technology to support transformation.

The firm provides services including corporate finance advisory, transaction strategy, and technology consulting. EY works with clients across areas such as healthcare, legal services, marketing, energy, finance, and government, with sustainability and innovation informing many of its solutions.

Senior AI Engineer, Generative AI and RAG — EY, Chennai Onsite

Build enterprise Generative AI, RAG, and conversational AI solutions for EY consulting clients. Contribute across implementation, validation, deployment, monitoring, and continuous improvement.

Description

  • Design, build, test, deploy, and support scalable AI, Generative AI, RAG, conversational AI, and agent-based solutions
  • Convert business requirements and solution designs into scalable components and reusable implementation patterns
  • Develop and maintain RAG pipelines, prompt workflows, retrieval systems, integrations, APIs, and automation components
  • Partner with architects, managers, data scientists, data engineers, application developers, and business stakeholders
  • Contribute across the AI solution lifecycle, from requirements and design through development, testing, deployment, monitoring, and improvement
  • Implement evaluation methods, validation processes, guardrails, quality controls, and performance optimization
  • Apply Responsible AI, data privacy, security, compliance, and risk-management practices
  • Produce technical documentation, implementation notes, test results, solution walkthroughs, and stakeholder updates
  • Support solution testing, validation, monitoring, issue resolution, and user adoption
  • Build reusable components, accelerators, implementation templates, and solution documentation
  • Support project leads with technical updates, demonstrations, walkthroughs, estimates, and delivery reporting
  • Mentor junior colleagues and contribute to AI practice capability development
  • Keep current with Generative AI, AI agents, multimodal AI, RAG architectures, prompt engineering, and enterprise AI platforms

Requirements

  • 4–8 years of professional experience, including hands-on work in AI/ML, Generative AI, data engineering, cloud AI platforms, or enterprise application development
  • Demonstrated enterprise, pre-production, or production experience delivering AI solutions; certifications, personal projects, and demos alone do not meet this requirement
  • Ability to discuss one or two AI or Generative AI implementations, including the business use case, personal contribution, technical approach, and outcomes
  • Practical experience with AI, Generative AI, Copilot, conversational AI, agentic AI, or RAG solutions in enterprise or client-facing settings
  • Working knowledge of LLM application development, RAG pipelines, prompt engineering, vector databases, AI evaluation, APIs, cloud deployment, MLOps, or LLMOps
  • Ability to collaborate effectively with architects, managers, developers, data engineers, and business stakeholders
  • Exposure to Azure AI Foundry, Azure OpenAI, Databricks, Microsoft Copilot, vector databases, or related enterprise AI ecosystems
  • Bachelor’s or master’s degree in Computer Science, Data Science, Engineering, Information Technology, or a related discipline
  • Strong understanding of large language models, Generative AI, RAG architectures, prompt engineering, conversational AI, and AI agents
  • Hands-on experience building or supporting Generative AI applications, copilots, chatbots, knowledge-search tools, AI agents, or automation workflows
  • Experience with Azure AI Foundry, Azure OpenAI, Databricks, vector databases, enterprise search, orchestration frameworks, and APIs
  • Ability to build or support retrieval pipelines, embeddings, prompt workflows, data ingestion, model integration, and application integration
  • Understanding of AI evaluation, guardrails, hallucination detection, quality metrics, observability, security, privacy, and Responsible AI
  • Working knowledge of software engineering, cloud deployment, APIs, databases, version control, CI/CD, MLOps, or LLMOps
  • Ability to troubleshoot technical issues, improve performance, document implementations, and support production or pre-production AI solutions
  • Strong analytical, problem-solving, collaboration, and communication abilities

Benefits

  • Ongoing learning and professional development opportunities
  • Access to tools and flexibility for delivering meaningful work
  • Coaching and leadership development focused on building confidence
  • Diverse and inclusive workplace culture
  • Opportunities to work with global clients and recognized brands
  • Collaboration with AI experts, analytics leaders, and industry specialists
  • Projects spanning multiple client sectors
  • Career pathways across EY Global Delivery Services

Related Jobs

Ambush

Senior Machine Learning and AI Engineer

Ambush

Build production-grade generative AI and agent workflows for Ambush’s financial services clients. Develop Python and FastAPI services, SQL data workflows, retrieval-augmented generation, and cloud-based AI systems.

Open