Principal Specialist - AI Application Full Stack

Overview

Design and build production-quality full-stack AI applications, including conversational AI, Generative AI, intelligent workflow and agentic experiences, for RTX Enterprise Services.

What you'll do

• Design and develop production-quality full-stack AI applications using modern frontend technologies such as React and TypeScript and backend technologies such as Python, Node.js, Java, or .NET.
• Build intuitive user experiences for conversational AI, Generative AI, intelligent workflows, and agentic applications, including streaming responses, dynamic content, citations, evidence, and AI-generated artifacts.
• Develop application-specific backend services, backend-for-frontend APIs, asynchronous workflows, application state, and integrations required to deliver complete end-to-end AI experiences.
• Build human-in-the-loop experiences that allow users to review, approve, modify, reject, pause, resume, cancel, or override AI and agent actions.
• Design application experiences that communicate agent activity, progress, tool execution, uncertainty, partial completion, errors, retries, and recovery.
• Integrate applications with enterprise AI services, agent runtimes, platform APIs, identity services, enterprise applications, data sources, and other backend systems.
• Develop reusable application components and patterns while ensuring accessibility, performance, security, automated testing, maintainability, and alignment with enterprise design systems.
• Partner closely with AI Product Design, Applied AI, Platform Engineering, and product teams from early prototypes through production deployment and continuous improvement.

What you'll need

• A Bachelor's Degree in Computer Science or Software Engineering.
• Minimum of 5 years of relevant professional experience.
• A minimum of 3 years of hands-on full-stack software development experience, including experience building production web applications using modern frontend frameworks and backend APIs or services.
• Strong hands-on experience with JavaScript or TypeScript and a modern frontend framework such as React, Next.js, Angular, or Vue.
• Backend development experience using Python, Node.js, Java, .NET, or similar technologies, including building and consuming REST APIs, microservices, and application services.
• Experience with application architecture, authentication and authorization, state management, asynchronous processing, databases, API integration, and enterprise application integration.
• Strong software engineering fundamentals including source control, code reviews, automated testing, CI/CD, debugging, performance optimization, security, and maintainable code.
• Hands-on experience integrating Generative AI, LLM APIs, AI services, or other AI-enabled capabilities into software applications.
• Experience taking features or applications from design through development, testing, deployment, and production support.

Nice to have

• Experience building production conversational AI, Generative AI, or agentic applications.
• Experience implementing streaming interfaces using Server-Sent Events, WebSockets, or similar technologies and supporting asynchronous or long-running AI workflows.
• Experience working with structured model outputs, tool calls, retrieval results, citations, RAG, agent state, or other AI-native application patterns.
• Experience building human-in-the-loop approvals, agent-control experiences, workflow applications, developer tools, technical consoles, or configuration-heavy enterprise products.
• Working knowledge of LLMs, agents, tools, context, memory, evaluation, guardrails, AI observability, and emerging interoperability approaches such as MCP.
• Experience deploying applications using containers, cloud services, Kubernetes, CI/CD, and modern DevOps practices.
• Experience with enterprise design systems, accessibility standards, responsive design, application telemetry, and production performance monitoring.
• Experience using AI-assisted coding and development tools to accelerate design implementation, coding, testing, debugging, documentation, and delivery.

Details

• Location: Bengaluru, Karnataka, India (Northgate, Sy No 2/2 Venkatala Village, Yelahanka Hobli).
• Work mode: Hybrid, with the ratio of onsite time determined in partnership with your leader.
• Commuting to and from the assigned site is the employee's personal responsibility.