AI Engineer-Senior

Role Overview: At EY, you will have the opportunity to build a unique career with global scale support, an inclusive culture, and cutting-edge technology to help you become the best version of yourself. Your unique voice and perspective are essential in contributing to making EY even better. Joining EY will not only provide you with an exceptional experience but also contribute to creating a better working world for all. Key Responsibilities: - Develop and implement AI and GenAI-based microservices and APIs using frameworks such as LangChain, LlamaIndex, or Semantic Kernel. - Work with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks to deliver intelligent, scalable, and secure enterprise solutions. - Build and maintain RAG pipelines involving embedding generation, document chunking, and vector search using tools like FAISS, Pinecone, or Weaviate. - Implement prompt engineering, fine-tuning, and model evaluation techniques to optimize responses and accuracy. - Deploy AI models and services using cloud AI platforms like AWS Bedrock, Azure AI, or Vertex AI. - Collaborate with cross-functional teams to convert solution blueprints into implementable modules. - Participate in technical discussions, design reviews, and sprint planning to ensure smooth delivery. - Support project managers in defining realistic timelines and technical dependencies. Qualifications Required: - Education: BE/BTech/MCA with a total of 4-8 years of experience, including at least 12 years of relevant AI/ML or GenAI project experience. - Mandatory Skills: Proficiency in Python (preferred), Java, LangChain, LlamaIndex, Hugging Face Transformers, OpenAI API, Azure OpenAI, Anthropic API, Pinecone, FAISS, Chroma, AWS Bedrock, Azure Cognitive Services, Google Vertex AI, REST/gRPC APIs, Swagger/OpenAPI, Postman, MySQL, MongoDB, Redis, Git, Docker, Kubernetes, CI/CD (GitHub Actions, Jenkins), PyTest, and version control with Git/GitHub or Bitbucket. - Preferred Skills: Experience with prompt optimization and evaluation, familiarity with LangGraph or CrewAI, basic knowledge of transformer architecture internals, working with data pipelines (Airflow, Prefect), awareness of responsible AI and model governance principles, and Agile/DevOps delivery experience. Company Details: EY Global Delivery Services (GDS) is a dynamic and global delivery network operating across multiple locations worldwide. The GDS teams play a crucial role in delivering the EY growth strategy by collaborating with teams from various service lines, geographies, and sectors. EY offers diverse career opportunities where you can work on exciting projects with well-known brands, continuously learn, and develop leadership skills in a diverse and inclusive culture. EY is committed to building a better working world by creating long-term value for clients, people, and society, while fostering trust in the capital markets. EY teams in over 150 countries provide assurance, consulting, legal, strategic, tax, and transaction services, aiming to find new answers to complex global challenges. Role Overview: At EY, you will have the opportunity to build a unique career with global scale support, an inclusive culture, and cutting-edge technology to help you become the best version of yourself. Your unique voice and perspective are essential in contributing to making EY even better. Joining EY will not only provide you with an exceptional experience but also contribute to creating a better working world for all. Key Responsibilities: - Develop and implement AI and GenAI-based microservices and APIs using frameworks such as LangChain, LlamaIndex, or Semantic Kernel. - Work with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks to deliver intelligent, scalable, and secure enterprise solutions. - Build and maintain RAG pipelines involving embedding generation, document chunking, and vector search using tools like FAISS, Pinecone, or Weaviate. - Implement prompt engineering, fine-tuning, and model evaluation techniques to optimize responses and accuracy. - Deploy AI models and services using cloud AI platforms like AWS Bedrock, Azure AI, or Vertex AI. - Collaborate with cross-functional teams to convert solution blueprints into implementable modules. - Participate in technical discussions, design reviews, and sprint planning to ensure smooth delivery. - Support project managers in defining realistic timelines and technical dependencies. Qualifications Required: - Education: BE/BTech/MCA with a total of 4-8 years of experience, including at least 12 years of relevant AI/ML or GenAI project experience. - Mandatory Skills: Proficiency in Python (preferred), Java, LangChain, LlamaIndex, Hugging Face Transformers, OpenAI API, Azure OpenAI, Anthropic API, Pinecone, FAISS, Chroma, AWS Bedrock, Azure Cognitive Services, Google Vertex AI, REST/gRPC APIs, Swagger/OpenAPI, Postman, MySQL, MongoDB, Redis, Git, Docker, Kubernetes, CI/CD (GitH