Senior AI Engineer

Apple Apple · Big Tech · Austin, TX +2 · Sales and Business Development

Senior AI Engineer role focused on building and operating LLM-powered applications and agentic AI systems for Apple Sales. Responsibilities include designing, prototyping, and productionizing intelligent agents, retrieval pipelines, and embedded AI features, integrating structured and unstructured data, and leading technical decisions on infrastructure and safety mechanisms. Requires strong Python, LLM, RAG, and agent orchestration framework experience.

What you'd actually do

  1. Design, prototype, and productionize LLM-powered applications that combine structured data, unstructured knowledge, semantic layers, and internal business logic
  2. Build agentic AI systems that can retrieve context, reason across data sources, call tools and APIs, generate insights, and support business decision-making.
  3. Partner with product, data science, design, engineering, and business stakeholders to translate ambiguous business problems into practical AI solutions
  4. Build modular APIs, SDKs, and micro-services to integrate LLMs, RAG pipelines, traditional ML models, data pipelines, and enterprise systems.
  5. Design secure and reliable integrations between LLMs, internal APIs, databases, knowledge sources, and enterprise tools.

Skills

Required

  • Python (FastAPI, LangChain, or similar frameworks)
  • Context engineering
  • RESTful API design
  • LLM APIs
  • Embeddings
  • Vector databases
  • RAG workflows
  • Data structures
  • Async programming
  • Pipeline orchestration
  • Agent orchestration frameworks (LangGraph, Google ADK, CrewAI, AutoGen, or similar)
  • Claude Code-style agentic engineering patterns
  • Business-context layers design
  • Telemetry and evaluation frameworks for AI agents

Nice to have

  • Tool calling
  • Multi-step reasoning flows
  • Agent handoffs
  • Memory/session management
  • Human-in-the-loop patterns
  • Knowledge graphs
  • Hybrid retrieval
  • Reranking
  • Graph-based approaches to enterprise knowledge modeling
  • Distributed systems architecture
  • Asynchronous messaging
  • Agent communication
  • RabbitMQ
  • Redis
  • Valkey

What the JD emphasized

  • 10+ years of experience in ML, software engineering, or data science, with recent focus on Applied AI and LLMs
  • Ability to lead development of AI projects from start to finish
  • Proficiency in Python (FastAPI, LangChain, or similar frameworks), context engineering, and RESTful API design
  • Hands-on experience with LLM APIs, embeddings, vector databases, and RAG workflows
  • Experience with agent orchestration frameworks such as LangGraph, Google ADK, CrewAI, AutoGen, or similar frameworks
  • Familiarity with Claude Code-style agentic engineering patterns, including subagents, hooks, MCP integrations, permissions, and session-based workflows
  • Ability to design business-context layers that combine structured data, semantic definitions, user permissions, domain logic, and unstructured knowledge to produce grounded AI responses
  • Hands-on experience building production-grade AI agents, including tool calling, routing, multi-step reasoning flows, agent handoffs, memory/session management, and human-in-the-loop patterns

Other signals

  • LLM-powered applications
  • Agentic AI systems
  • Retrieval pipelines
  • Embedded AI features
  • Production-grade AI agents