Job Description
At Starbucks, our mission is to inspire and nurture the human spirit – one person, one cup, and one neighborhood at a time. Starbucks Technologists work to achieve this mission through the use of cutting-edge technology delivered to our partners, customers, stores, roasters, and global communities. The Senior Software Engineer - AI Automation & Developer Productivity is a hands-on technical role within our Developer Productivity and Automation organization. This role focuses on designing, building, and operating shared cloud-native platforms and AI-powered automation that enable engineering teams to build, test, and release software more effectively at scale. This engineer brings a platform mindset, thrives in ambiguous problem spaces, enjoys getting hands-on with code, and partners closely with product, platform, DevOps, and SRE teams to deliver production-ready capabilities used by many teams across the organization. Responsibilities and essential job functions include but are not limited to the following: Designs, builds, and operates AI-powered automation and agent-based systems across multiple phases of the software development lifecycle (SDLC). Designs and builds shared cloud-native platforms, services, and frameworks that enable other engineering teams to build, deploy, and operate AI agents and automation safely and efficiently. Provides paved-road infrastructure, APIs, templates, and reference implementations that accelerate adoption of agentic and GenAI capabilities across multiple teams. Implements agentic workflows to analyze requirements, generate test scenarios, identify risks, and surface quality gaps early in the development cycle. Develops AI-driven solutions for automated testing, performance testing, quality validation, and A/B experimentation. Integrates AI-driven quality checks, code analysis, and validation into CI/CD pipelines in partnership with DevOps and SRE teams. Builds and maintains scalable automation frameworks for data processing, model execution, validation, and deployment. Writes clean, efficient, and well-structured software in an iterative, continuous delivery environment. Participates actively in design reviews, code reviews, and incident retrospectives to uphold engineering excellence. Evaluates emerging AI, GenAI, and automation tools through prototypes and proofs of concept, recommending scalable adoption strategies. Contributes to and promotes strong software engineering practices including testing, observability, documentation, and operational readiness. Communicates complex technical concepts clearly to both technical and non-technical stakeholders. Basic Qualifications 8-10 years of professional industry experience with software development 2 years of leading teams of four or more software developers Bachelor’s degree in Computer Science or related field engineer lead 7+ years of experience in system administration, network administration, and systems engineering 7+ years of experience in one or more of the following languages: C, C++, Java, Python, Go, Perl and/or Ruby. 5+ years Experience with large-scale distributed systems and client-server architectures Demonstrated ability to debug and optimize code, and automate routine tasks. Interest in designing, analyzing and troubleshooting large-scale distributed systems. Proven ability to translate insights into business recommendations Deep Knowledge in application development and supporting a development environment Experience with Cloud Computing platforms (e.g. Amazon AWS, Microsoft Azure, Google App Engine) Demonstrated experience implementing and managing high capacity, redundant, and mission critical environments Preferred Qualifications Experience applying Generative AI or AI/ML techniques to software development, quality engineering, or automation workflows. Experience building agentic or GenAI-powered systems using frameworks and platforms such as LangChain, AWS Bedrock, or similar orchestration and model hosting technologies. Familiarity with agentic AI concepts including LLM orchestration, autonomous agents, retrieval-augmented generation (RAG), prompt engineering, and vector databases. Experience designing enablement platforms, SDKs, or reusable services that allow other teams to build and extend AI-driven or automation workflows independently. Experience defining guardrails, abstractions, and operational standards that enable teams to safely adopt AI and agent-based systems at scale. Experience working with open-source LLMs and AI frameworks. Hands-on experience with data platforms and streaming technologies such as Kafka, Spark, Hadoop, or Databricks.