Engineer, AI [T500-27953]

TMUS Global Solutions; Hyderabad; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

TMUS Global Solutions, a T-Mobile subsidiary, seeks a senior software engineer to design and scale the AI platform powering agentic capabilities. You will craft orchestration frameworks, low-latency services, and reusable platform components for enterprise-scale AI workflows.

You will collaborate with AI/ML and platform teams to integrate models, tooling, and data sources, ensuring reliability, performance, and secure access across multiple enterprise systems.

Qualifications

• 7+ years of software engineering experience building distributed systems.
• Strong proficiency in Python or Java, with working knowledge of both preferred.
• Experience designing APIs, microservices, workflow engines, or platform services.
• Experience building systems that integrate with LLMs, AI services, or conversational platforms.
• Experience designing highly available distributed systems and service-oriented architectures.
• Strong understanding of software architecture, system design, scalability, resiliency, and performance optimization.
• Demonstrated experience leading technical design discussions, driving architectural decisions, and influencing engineering direction across teams.
• Experience with cloud-native technologies, including containers, Kubernetes, and service-based architectures.
• Excellent problem-solving, debugging, and technical communication skills.
• Bachelor’s degree in Computer Science, Software Engineering, Information Systems, or a related field, or equivalent practical experience.

Responsibilities

• Design and develop agent orchestration frameworks and execution engines supporting complex AI-driven workflows.
• Design and optimize low-latency services supporting real-time conversational and voice interactions.
• Build reusable platform services, SDKs, APIs, and libraries that accelerate development of conversational AI applications.
• Design and implement Model Context Protocol (MCP) integrations and frameworks that enable secure, scalable access to enterprise tools, APIs, data sources, and agent capabilities.
• Develop reusable tool-calling, context-sharing, and interoperability services that support MCP-enabled agent ecosystems.
• Develop runtime services for text- and voice-based agent interactions, including context management, tool execution, memory, and state orchestration.
• Architect microservices and event-driven systems that integrate AI reasoning with enterprise systems.
• Design mechanisms that safely translate model outputs into deterministic business actions and workflows.
• Collaborate with AI/ML engineers to integrate foundation models, retrieval systems, evaluation frameworks, and agent capabilities into production platforms.
• Drive platform reliability, scalability, observability, and performance across high-volume AI workloads.

Skills

Python software engineering

Distributed systems

APIs and microservices

LLM integration

Cloud-native architecture

Education

Bachelor's degree in Computer Science or related

Tools

Kubernetes

Job description

T-Mobile US, Inc. (NASDAQ: TMUS) is America’s supercharged Un-carrier, powered by an award-winning 5G network that connects more people in more places than ever before. With its unique value proposition of best network, best value, and best experiences, T-Mobile is redefining connectivity, fueling competition, and driving the next wave of innovation in wireless and beyond. Headquartered in Bellevue, Washington, T-Mobile provides services through its subsidiaries and operates its flagship brands, T-Mobile, Metro by T-Mobile, and Mint Mobile.

TMUS Global Solutions

TMUS Global Solutions is a world-class technology organization accelerating T-Mobile’s global digital transformation. Our teams combine engineering talent, technology expertise, and collaborative ways of working to build secure, scalable solutions that improve customer and employee experiences. We foster innovation, agility, transparency, and strong enterprise partnerships to deliver measurable business outcomes.

About the Role

This role is responsible for designing, building, and scaling the foundational software platform that powers T-Mobile’s agentic AI capabilities across conversational experiences, including text and voice interactions. The engineer develops the core execution, orchestration, and integration frameworks that enable AI systems to reason, plan, act, and interact safely with enterprise services at scale, while providing technical leadership for the architecture, evolution, and scalability of the AI execution platform.

Working closely with AI/ML engineers, platform engineers, product teams, and enterprise application teams, this role focuses on building reusable platform capabilities rather than individual AI applications. Responsibilities include designing agent orchestration frameworks, workflow execution engines, SDKs, tool integration layers, memory and state management systems, and conversational runtime services that support next-generation customer and employee experiences.

Success in this role requires strong software engineering expertise, distributed systems knowledge, and practical understanding of LLM-powered systems, with an emphasis on reliability, extensibility, scalability, and platform adoption. We pride ourselves on encouraging a culture of innovation, agile ways of working, and transparency in all we do. Join us in embodying the spirit of the Un-carrier and making a tangible impact.

What You'll Do

• Design and develop agent orchestration frameworks and execution engines supporting complex AI-driven workflows.
• Design and optimize low-latency services supporting real-time conversational and voice interactions.
• Build reusable platform services, SDKs, APIs, and libraries that accelerate development of conversational AI applications.
• Design and implement Model Context Protocol (MCP) integrations and frameworks that enable secure, scalable access to enterprise tools, APIs, data sources, and agent capabilities.
• Develop reusable tool-calling, context-sharing, and interoperability services that support MCP-enabled agent ecosystems.
• Develop runtime services for text- and voice-based agent interactions, including context management, tool execution, memory, and state orchestration.
• Architect microservices and event-driven systems that integrate AI reasoning with enterprise systems such as customer, billing, network, and support platforms.
• Design mechanisms that safely translate model outputs into deterministic business actions and workflows.
• Collaborate with AI/ML engineers to integrate foundation models, retrieval systems, evaluation frameworks, and agent capabilities into production platforms.
• Drive platform reliability, scalability, observability, and performance across high-volume AI workloads.
• Establish software architecture standards, engineering best practices, and reusable design patterns for agentic systems.
• Contribute to technical strategy and platform evolution by evaluating emerging AI, orchestration, and distributed systems technologies.
• Mentor engineers and promote engineering excellence through design reviews, documentation, and knowledge sharing.

What You'll Bring

• 7+ years of software engineering experience building distributed systems and cloud-native applications.
• Strong proficiency in Python or Java, with working knowledge of both preferred.
• Experience designing APIs, microservices, workflow engines, or platform services.
• Experience building systems that integrate with LLMs, AI services, or conversational platforms.
• Experience designing highly available distributed systems and service-oriented architectures.
• Strong understanding of software architecture, system design, scalability, resiliency, and performance optimization.
• Demonstrated experience leading technical design discussions, driving architectural decisions, and influencing engineering direction across teams.
• Experience with cloud-native technologies, including containers, Kubernetes, and service-based architectures.
• Excellent problem-solving, debugging, and technical communication skills.
• Bachelor’s degree in Computer Science, Software Engineering, Information Systems, or a related field, or equivalent practical experience.
• Experience integrating AI systems with enterprise applications, APIs, tools, or data platforms through standardized integration patterns.

Must Have Skills

• Python software engineering
• Distributed systems, APIs, and microservices
• LLM, AI service, and conversational platform integration
• Cloud-native architecture, containers, and Kubernetes
• Software architecture and technical leadership

Nice-to-Have

• Experience building agent orchestration frameworks, workflow platforms, or AI execution systems.
• Experience with conversational AI, voice platforms, speech technologies, or real-time interaction systems.
• Familiarity with retrieval systems, vector databases, memory architectures, and evaluation frameworks.
• Knowledge of event-driven architectures, distributed workflows, and enterprise integration patterns.
• Experience with Model Context Protocol (MCP), agent tool-calling frameworks, or similar standards for connecting AI systems with external tools and services.
• Experience designing reusable tool integration frameworks, context management systems, or agent interoperability platforms.