At Apple, the business problem is to accelerate app development inside the company by building a next-gen developer experience platform, which requires designing and implementing various developer front-end tools.
Requirements
- Hands-on experience building AI agents with Large Language Models (LLMs), including Retrieval-Augmented Generation (RAG), using frameworks such as LangChain, LangGraph, Pydantic AI, or CrewAI
- Strong programming skills in multiple languages (e.g., Python, Java, Go, Node.js, or TypeScript), with solid experience designing and developing distributed systems, backend services, and APIs in production environments
- Familiarity with deploying and operating services in cloud environments (AWS, GCP, or Azure), including containerization (Docker) and orchestration (Kubernetes)
- Experience with CI/CD pipelines and MLOps practices for deploying, scaling, and monitoring LLM-powered services
- Background in building REST or GraphQL APIs, microservices, and event-driven systems
- Knowledge of vector databases, memory systems, and human-in-the-loop workflows
Responsibilities
- Design and maintain backend services and orchestration systems that power multi-agent AI workflows.
- Build reliable systems that integrate large language models (LLMs) into developer tools and services.
- Work on cloud deployments, CI/CD, and MLOps practices to keep AI services reliable and scalable.
- Collaborate with researchers and engineers to bring new AI capabilities into production.
- Partner with developers to understand their needs and improve the experience of using AI-powered tools.
Other
- Bachelor’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field, or equivalent practical experience
- 4+ years of industry experience in software engineering or machine learning
- Strong collaboration skills with the ability to work effectively across ML research, platform engineering, and product teams
