Software Engineer II (GenAI)

AI EngineerDisney Entertainment and ESPN Product & Technology is a global organization of engineers, product developers, designers, technologists, data scientists, and more – all working to build and advance the technological backbone for Disney's media business globally.The team marries technology with creativity to build world-class products, enhance storytelling, and drive velocity, innovation, and scalability for our businesses. We are Storytellers and Innovators. Creators and Builders. Entertainers and Engineers. We work with every part of The Walt Disney Company's media portfolio to advance the technological foundation and consumer media touch points serving millions of people around the world.We are looking for an AI Engineer to help build and support enterprise Generative AI applications. This role will contribute to our conversational AI platform for enabling natural language interaction with enterprise operational data.The role focuses on hands on GenAI application engineering, including Python development, retrieval and grounding workflows, prompt design, conversational AI support, and backend service integration. It also includes direct exposure to production GenAI practices, including LLMOps across evaluation, observability, deployment support, agentic workflows, tool calling, MCP style integrations, and production troubleshooting.The ideal candidate can build, debug, learn quickly, use AI developer tools effectively, and contribute to reliable production GenAI systems. Azure experience is a plus.Responsibilities and Duties of the Role:Build and maintain Python based GenAI application componentsConnect conversational AI workflows with backend services, web applications, and internal toolsImplement retrieval and grounding workflows that support source backed AI responsesDevelop prompt logic, response formatting, structured outputs, and validation patternsAssist with document ingestion, semantic chunking, metadata handling, and retrieval testingSupport agentic workflows involving tool use, function calling, API actions, and multi step reasoningLearn and contribute to MCP style integration patterns for connecting AI systems to tools, data, and enterprise servicesSupport LLMOps practices, including observability, logging, monitoring, evaluation, latency tracking, cost tracking, and production troubleshootingHelp create and maintain validation datasets, regression tests, and response quality review workflowsAssist with deployment support, environment configuration, and operational documentationUse AI developer tools such as Cursor, Claude Code, or similar tools as part of the required engineering workflow to improve velocity, code understanding, testing, and documentation qualityWork with senior engineers to improve reliability, maintainability, and transparency of GenAI systemsRequired Education, Experience/Skills/Training:3+ years of professional software development experienceStrong Python development skillsHands on experience or project work with GenAI applications or conversational AI systemsFamiliarity with retrieval based GenAI patterns, grounding, embeddings, vector search, and prompt engineeringExperience integrating APIs and backend servicesHands on exposure to MCP, tool calling, function calling, or agentic integration patternsExposure to cloud application development in Azure, AWS, or GCPAbility to read logs, investigate issues, and troubleshoot application behaviorWorking knowledge of LLMOps concepts, including evaluation, observability, monitoring, deployment support, and production AI system reliabilityRequired use of AI assisted developer tools such as Cursor, Claude Code, or similar tools to support development velocity, documentation, code review preparation, and technical problem solvingBachelor's degree requiredPreferred Qualifications:Experience with Azure OpenAI, Azure AI Foundry, Azure Functions, Azure App Service, or Application InsightsExperience with Microsoft Teams bots or enterprise conversational interfacesFamiliarity with Snowflake Cortex, Cortex Analyst, semantic views, or natural language to SQL workflowsExperience with MongoDB, Atlas Vector Search, or graph databasesExperience testing AI responses against expected answers, source data, or user feedbackExposure to CI/CD, Docker, telemetry, and deployment pipelinesInterest in secure enterprise AI patterns, grounding, access control, and responsible AI behaviorThe hiring range for this position in Seattle, WA is $123,000.00 to $165,000.00 per year, and in Glendale, CA is $117,500.00 to $157,500.00 per year. The base pay actually offered will take into account internal equity and also may vary depending on the candidate's geographic region, job-related knowledge, skills, and experience among other factors. A bonus and/or long-term incentive units may be provided as part of the compensation package, in addition to the full range of medical, financial, and/or other benefits, dependent on the level and position offered.