Generative AI Engineer / Architect with Google Cloud Platform (GCP)

Tata Consultancy Services Limited; Hyderabad, Chennai, Bengaluru; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Tata Consultancy Services Limited seeks seasoned professionals to design and deliver GenAI and LLM-driven solutions on Google Cloud Platform. You will architect RAG pipelines, create AI agents and copilots, and implement robust MLOps, security and governance across enterprise-scale deployments.

Join a team translating business use cases into production-grade GenAI solutions with a strong focus on responsible AI, data privacy, and cost optimization.

Qualifications

• Experience designing and developing GenAI and LLM-based applications on GCP.
• Experience building RAG systems using enterprise data.
• Proficiency in building AI agents, copilots, and conversational AI.
• Expertise in prompt engineering, grounding, evaluation, and optimization of GenAI.
• APIs and microservices design for enterprise integration.
• Document ingestion, embedding, vector search and retrieval pipelines.
• Scalable cloud-native GenAI architectures with security and governance.
• LLMOps/MLOps practices across development, deployment and monitoring.

Skills

Generative AI

LLM-based applications

Prompt engineering

AI agents / copilots

Conversational AI

APIs & Microservices

RAG (Retrieval-Augmented Generation)

LLMOps / MLOps

Security & governance

Data privacy & cost optimization

Monitoring & lifecycle management

Tools

Google Cloud Platform (GCP)

Job description

Preferred candidate profile

• Design and develop Generative AI and LLM-based applications on GCP.
• Build enterprise RAG (Retrieval-Augmented Generation) solutions using organizational documents and structured/unstructured data.
• Develop AI agents, conversational AI solutions, copilots and intelligent assistants for business use cases.
• Perform prompt engineering, grounding, evaluation and optimization of GenAI applications.
• Design APIs and microservices for integrating AI capabilities with enterprise applications.
• Implement document ingestion, chunking, embedding, vector search and retrieval pipelines.
• Build scalable cloud-native GenAI architectures incorporating security, identity, monitoring and governance.
• Establish LLMOps/MLOps practices covering development, deployment, monitoring and model/application lifecycle management.
• Work with business, cloud, data and application teams to translate use cases into production AI solutions.
• Address enterprise requirements around responsible AI, data privacy, security, hallucination control and cost optimization.