Sr AI Engineer

T-Mobile•Bellevue, WA

About The Position

T-Mobile is seeking a Senior AI Engineer to design and optimize agentic AI systems that support next-generation customer experiences and customer service automation. The role focuses on building reliable, production-grade Generative AI applications and workflows that coordinate across models, internal APIs, enterprise data, and third-party tools. The engineer will use techniques including prompt engineering, model fine-tuning, evaluation frameworks, retrieval optimization, and system-level orchestration to improve AI accuracy, reliability, and reasoning capabilities. The position works closely with engineering, product, operations, architecture, cybersecurity, and business teams to integrate AI enhancements into resilient, fault-tolerant production environments. It also contributes to engineering standards through design and code reviews, mentoring, and research into emerging AI technologies. Travel is not required.

Requirements

Strong proficiency in Python, software engineering principles, and object-oriented programming.
Experience designing, developing, securing, and integrating RESTful APIs using FastAPI or an equivalent framework.
Hands-on experience building applications with large language models, prompt engineering, structured outputs, function calling, and tool integration.
Experience developing AI agents, tool-calling workflows, and orchestration solutions using LangGraph, LangChain, or similar frameworks.
Knowledge of embeddings, vector databases, semantic retrieval, document processing, and data integration.
Experience developing and deploying applications on Azure, AWS, or Google Cloud.
Proficiency with Git, CI/CD pipelines, automated testing, and production software development practices.
Ability to design scalable, secure, reliable, and maintainable distributed applications.
Strong analytical skills and experience working with structured and unstructured data.
Understanding of model evaluation, performance benchmarking, accuracy measurement, and AI quality assurance.
Strong communication, problem-solving, and cross-functional collaboration skills.
Bachelor's degree plus 5 years of related work experience, or an advanced degree plus 3 years of related work experience.
At least 18 years of age.
Legally authorized to work in the United States.

Nice To Haves

Experience with Model Context Protocol (MCP) and enterprise AI tool integrations.
Experience with Docker, Kubernetes, and cloud-native deployment tooling for AI workloads.
Acceptable preferred areas of study include Computer Science, Artificial Intelligence, or a related field; a master's or advanced degree in Computer Science, Artificial Intelligence, or Data Science is preferred.
Four or more years of experience developing and optimizing AI models for customer service automation using techniques such as prompt engineering and fine-tuning.
Four or more years of experience architecting and deploying agentic AI systems for improved reasoning and interaction in complex workflows.
Four or more years of experience collaborating with cross-functional teams to integrate AI-driven enhancements into production systems.
Certified Analytics Professional (CAP) certification.
NVIDIA Deep Learning AI Certification.
Certified Data Scientist (CDS) certification.

Responsibilities

Design, develop, and deploy scalable, production-grade Generative AI applications, LLM-powered solutions, and agentic AI systems for enterprise operations and customer service automation.
Architect and implement AI agents and multi-agent orchestration workflows using LangGraph, LangChain, or equivalent frameworks.
Develop Retrieval-Augmented Generation (RAG) solutions using embeddings, vector databases, semantic search, and enterprise knowledge sources.
Build and integrate RESTful APIs, Model Context Protocol (MCP) connectors, and enterprise data services for secure AI interactions with internal and external systems.
Optimize AI performance through prompt engineering, model selection, retrieval optimization, fine-tuning, and efficient inference strategies.
Design and implement AI evaluation frameworks to measure accuracy, hallucination rates, reliability, latency, throughput, and cost efficiency.
Develop cloud-native AI solutions using Azure, AWS, or equivalent platforms, including containerization, automated deployment, and scalable architectures.
Implement security, governance, and responsible AI practices, including authentication, authorization, data privacy, prompt-injection protection, and enterprise compliance.
Establish observability, logging, monitoring, and troubleshooting capabilities for production AI applications and agentic workflows.
Collaborate with engineering, architecture, product, cybersecurity, and business teams to integrate AI enhancements into production systems.
Conduct technical design reviews, participate in code reviews, mentor engineers, and contribute to reusable engineering standards and best practices.
Research and evaluate emerging AI technologies, open-source frameworks, and industry advancements; identify opportunities for innovation and continuous improvement.
Perform other duties and projects as assigned by business management.

Benefits

Competitive base salary and compensation package, including an annual incentive opportunity at target performance.
Annual stock grant and employee stock purchase plan.
401(k).
Access to free, year-round money coaches.
Medical, dental, and vision insurance.
Flexible spending account.
Paid time off and up to 12 paid holidays.
Paid parental and family leave.
Family-building benefits, backup care, enhanced family support, and childcare subsidy.
Tuition assistance and college coaching.
Short- and long-term disability coverage.
Voluntary AD&D, accident, life, disability, and long-term care insurance.
Mobile service and home internet discounts for eligible employees.
Pet insurance for eligible employees.
Commuter and transit programs for eligible employees.