Apple
Systems Engineer - Evaluation Engineering
$150K–$278K
Cupertino, California · Full-time · Posted Oct 22, 2026
- Experience
- 7+ years.
- Education
- MS in computer science or equivalent.
About the job
Build and operate the distributed infrastructure that runs large-scale agent simulations and evaluation pipelines for Siri, including APIs, data processing, deployment, and observability.
What you'll do
- Architect and scale asynchronous systems for parallel simulations, validation tests, and model-judging pipelines.
- Build self-service developer infrastructure, APIs, and CI/CD integrations for ML and product teams.
- Develop trace data pipelines and platform reliability features, including observability, scheduling, and failure guardrails.
What they ask for
- MS in computer science or equivalent.
- 7+ years of experience as a distributed systems engineer, platform engineer, or equivalent.
- Strong proficiency in Python (asyncio) or Java.
- Advanced experience with Kubernetes and AWS, GCP, or Azure; deep expertise in production API design using gRPC/Protobuf, GraphQL, or REST (FastAPI).
Nice to have
- Experience with PostgreSQL and event-driven systems using Kafka, AWS SQS/SNS, RabbitMQ, or Redis Streams.
- Experience with Agentic RAG platforms, developer tooling, Terraform, or CI/CD tools such as GitHub or ArgoCD.
Pay
$150,400 and $277,600 (base salary range)
Tools
Python (asyncio), Java, gRPC/Protobuf, GraphQL, REST (FastAPI), Kubernetes, AWS, PostgreSQL
AI focus
Supports agentic simulations and multi-model evaluation pipelines, including LLM-as-a-judge workflows; the role builds the underlying platform infrastructure.
Model-written summary · the original posting is authoritative