Software Engineer - Evaluation Engineering
Core
Build foundational on-device execution harnesses and runtime infrastructure to validate multi-step agent trajectories for Apple Intelligence.
Role type
Senior IC systems engineer (evaluation infrastructure)
Builds
Low-level execution harnesses, environment control layers, and trace collection pipelines for agentic evaluation
Domain
Consumer electronics / AI evaluation infrastructure
Deliverable
production ML models
Required skills
Swift, C++, Objective-C, Python, process management, local runtimes, system architecture
Preferred skills
Apple platform development, environment-staging systems, telemetry infrastructure, on-device AI/LLM runtimes
Technologies
iOS, macOS, watchOS, visionOS, Python, C++, Swift
Responsibilities
Architect high-reliability execution harnesses for dynamic agent trajectories; Implement event-capture layers for high-fidelity execution traces; Build CLI tools and automation scripts for local development and testing pipelines; Optimize harness performance and resource overhead on heterogeneous hardware.
Seniority
Senior, hands-on IC