Senior Full-Stack Engineer - Web Platforms ML Inference

Senior Full-Stack Engineer - Web Platforms for ML Inference

Cupertino, California, United States Software and Services

Apple’s AIML organization powers intelligence across many of our most iconic experiences. Within AIML, the Annotation AI Services organization builds the foundational systems that enable large-scale model inference, data pipelines, and ML platform capabilities for annotation platforms.

We are looking for a Senior Full-Stack Engineer who enjoys working across modern web applications and cloud-native backend systems. This role is ideal for engineers who value end-to-end ownership—from designing polished, scalable React + Type Script web platforms to building and operating the cloud infrastructure and services that power them.

You will focus on web platforms used by annotation platforms and operation teams across Apple to discover, configure, and interact with inference services, pipelines, and ML infrastructure—helping make complex systems accessible, reliable, and scalable.

As a Senior Full-Stack Engineer on the Annotation AI Services team, you will design and build web platforms that sit at the front door of ML inference and pipeline systems.

You will create modern, high-quality React and Type Script applications while also developing cloud-native backend services deployed on AWS and Kubernetes. The role values engineers who appreciate working across the stack and who enjoy collaborating closely with infrastructure, ML systems, and platform teams to deliver cohesive, end-to-end solutions.

• Design, build, and maintain modern web applications using React and Type Script.
• Own frontend architecture, including:
• Component and state management patterns
• Performance, scalability, and responsiveness
• Secure and reliable API integrations
• Build web platforms that enable teams to:
• Discover and configure inference services
• Interact with ML pipelines and workflows
• Monitor usage, health, and operational signals
• Establish best practices around testing, maintainability, accessibility, and developer experience.
• Design and implement backend endpoints that power the product UI, with clear API contracts and pragmatic versioning/backward compatibility (REST and/or gRPC).
• Build reliable services in Python and/or Node.js with basic correctness patterns: input validation, auth checks, pagination, idempotency where needed, and sensible error handling.
• Work effectively in a Kubernetes + AWS environment: read logs/metrics, debug issues, and make safe, incremental changes to services that run on EKS (or equivalent).
• Security basics: service-to-service auth (OIDC/JWT/IAM patterns used internally), least-privilege mindset, and safe handling of secrets/config.
• Data integration for product features: use common persistence/messaging building blocks (e.g., DB + S3 + queue) and work within existing schema/migration workflows.

• 5+ years of professional software engineering experience.
• Strong experience building and shipping production web applications with React and Type Script (including testing and performance).
• Working backend experience with Python and/or Node.js building APIs and integrations used by frontend applications.
• Experience shipping and debugging services in a cloud environment (AWS preferred) and a containerized runtime (Kubernetes/EKS or equivalent preferred).
• Experience designing and consuming APIs for frontend-backend integration (REST and/or gRPC), including auth, pagination, and error handling.
• Solid fundamentals in web architecture and security (authentication/authorization and secure API design).
• Comfortable working across the stack and collaborating with product/design/backend/infrastructure partners.
• BS in Computer Science or equivalent practical experience.

• Experience building internal platforms or developer-facing tools.
• Familiarity with ML platforms, inference systems, or data pipelines.
• Experience with gRPC and/or Protobuf-based APIs.
• Exposure to observability systems (metrics, logging, tracing).
• Experience operating services in production Kubernetes environments.
• Experience with safe rollout strategies (e.g., canary or blue/green), autoscaling,…