Agent Development Engineer, Customer Systems

Apple
Apple

Customer Service

Cupertino, CA, USA

USD 181,100-272,100 / year + Equity

Posted on Jun 9, 2026
Customer Systems is part of IS&T and drives the technology behind Apple's customer support experience — from contact center operations to the software powering the iconic Genius Bar. The team also builds and operates AppleCare's online support platform, which handles 6 billion visits per year, delivering seamless, high-quality support to Apple customers around the globe. There are jobs and then there are opportunities! This is your opportunity to do the best work of your life. Join us, the team that serves as Apple’s nerve center: Apple Information Systems and Technology group! We are seeking a highly innovative and specialized Agent Development Engineer to design, build, and deploy autonomous AI systems. Unlike traditional software or chatbot developers, you will create intelligent agents that leverage Large Language Models (LLMs) to reason, plan, use tools, and execute multi-step actions independently to achieve specific goals, fundamentally transforming how Apple operates and delivers customer experiences. When you join IS&T, you’ll help design and manage systems, frameworks, and apps that countless Apple customers and employees rely on every day. Together, we’ll explore all the ways to improve how Apple operates, freeing our employees to do what they do best, and crafting magical experiences for our customers!
As an Agent Development Engineer, you will be at the forefront of building the next generation of intelligent automation. Your core responsibilities will include:• Design & Architecture: Creating the foundational architecture for AI agents, including sophisticated reasoning engines that break down complex problems and robust decision-making workflows. Agent Development: Building autonomous agents using cutting-edge frameworks like LangChain, LangGraph, AutoGen, or CrewAI. Tool Integration & API Usage: Connecting agents to external tools, databases, APIs, and critical business systems to enable seamless action-taking and interaction with the broader ecosystem. Memory & Context Management: Implementing advanced short- and long-term memory systems (e.g., using vector databases, RAG) so agents can remember past interactions, learn from experience, and maintain context across complex tasks. Prompt Engineering & Optimization: Authoring complex, domain-specific prompts and designing sophisticated chain-of-thought workflows to guide agent reasoning and ensure optimal performance. Testing & Reliability: Implementing “human-in-the-loop” systems, developing comprehensive evaluation frameworks (evals), and establishing safety guardrails to ensure agents behave reliably, ethically, and predictably in production environments. Deployment & Scaling: Deploying agents into production environments, often leveraging Docker, Kubernetes, and cloud platforms like AWS/Azure/GCP, ensuring scalability and high availability. The ideal candidate will possess a unique blend of software engineering rigor and AI innovation. You will thrive in an environment where systems are non-deterministic, requiring continuous testing, monitoring, and adaptation. A strong focus on the end-to-end behavior of goal-driven systems, rather than just isolated model optimization, is crucial. You should be passionate about process automation and understand how AI agents can replace or augment traditional Robotic Process Automation (RPA), requiring a keen understanding of business workflows. Excellent communication and collaboration skills are essential for working with diverse teams across Apple.
  • B.S. in Computer Science, Computer Engineering, or a related technical field, or equivalent professional work experience.
  • 7+ years proven experience developing software in a professional capacity. Longer experience preferred.
  • 2+ years of professional software development experience, with a strong focus on backend systems or AI/ML applications.
  • Strong proficiency in TypeScript, with experience in developing robust, scalable applications.
  • Experience with at least one major AI Agent framework such as LangChain, AutoGen, LangGraph, or Semantic Kernel.
  • Deep understanding of Large Language Models (LLMs), including their capabilities, limitations, and practical application (e.g., GPT-4o, Claude 3.5 Sonnet, Gemini).
  • Practical experience with Retrieval-Augmented Generation (RAG) and fine-tuning techniques for LLMs.
  • Experience with vector databases (e.g., Pinecone, Milvus, Qdrant) and traditional SQL/NoSQL databases.
  • Proficiency with cloud platforms (AWS, Azure, GCP) and containerization tools (Docker, Kubernetes) for deployment and management.
  • Experience in AI, machine learning, or automation systems beyond basic scripting.
  • Background as a Machine Learning Engineer or Full-Stack Developer with a strong interest in autonomous systems.
  • Familiarity with JavaScript or TypeScript for agent front-end integration or tooling.
  • Experience designing and implementing complex multi-agent systems or agentic workflows.
  • Understanding of ethical AI principles, bias detection, and mitigation strategies in agent design.
  • Contributions to open-source AI agent frameworks or relevant research.
  • Demonstrated ability to translate complex business problems into agent-based solutions.