Join our innovative team at NTT DATA and contribute to the development of cutting-edge GenAI agentic solutions. This role focuses on enhancing the management of large-scale production environments by creating AI agents capable of diagnosing issues, reasoning through problems, and taking automated actions.

Advance productivity and resolve production support challenges with intelligent AI-driven solutions. You will play a key part in building systems that improve operational efficiency and reduce risk in complex production landscapes.

NTT DATA is a global leader in business and technology services, committed to accelerating client success and positively impacting society through responsible innovation. We are seeking passionate individuals eager to grow with us in an inclusive and forward-thinking organization.

Design and implement sophisticated tool-calling agents that integrate retrieval, structured reasoning, and secure action execution using MCP protocol. Develop robust guardrails to ensure safety, compliance, and least-privilege access.

Engineer evaluation frameworks for various LLMs, productionize them with retrieval pipelines, prompt synthesis, and self-correction loops. Integrate these agents with runtime ecosystems like observability and incident management for automated diagnostics and remediation.

Collaborate closely with production engineers and application teams to translate real-world pain points into actionable agentic AI roadmaps. Focus on delivering auditable, business-aligned outcomes that improve reliability, reduce risk, and optimize costs.

Build and maintain RAG pipelines, curating domain knowledge and establishing feedback loops for knowledge freshness. Drive design reviews, promote rigorous experimentation, and mentor peers on agent architectures and safe deployment strategies.

A strong foundation in software development with 5+ years of experience in languages like Python, C/C++, Go, or Java is essential; extensive Python application development is highly preferred.

Possess 3+ years of experience in designing, architecting, and launching production ML systems, covering model deployment, evaluation, monitoring, and data processing pipelines.

Demonstrate practical expertise with Large Language Models (LLMs), including API integration, prompt engineering, fine-tuning, and building applications using RAG and tool-using agents. A solid understanding of various LLMs and their capabilities is required.

Excellent analytical problem-solving skills, a strong sense of ownership, and the ability to communicate complex ideas clearly are vital. Proficiency in cloud infrastructure, particularly AWS, and containerized services is preferred. This role requires a commitment to in-office presence five days a week in Bangalore.