Drimva

Apple

Software Engineer - Evaluation Engineering

$150K–$225K

Cupertino, California · Full-time · Posted Jun 9, 2026

Education
B.S. or M.S. in Computer Science, Machine Learning, or equivalent experience.

About the job

Build on-device execution harnesses and runtime infrastructure to simulate and evaluate multi-step AI agent behavior across Apple hardware.

What you'll do

  • Build reliable harnesses for agent trajectories and tool interactions on Apple devices.
  • Develop event-capture layers and trace pipelines for downstream scoring and analysis.
  • Create automation and integration tools, and optimize harness performance and resource usage.

What they ask for

  • Strong programming proficiency in compiled languages (Swift, C++, or Objective-C).
  • Scripting and automation skills in Python.
  • Solid computer science and systems fundamentals, including process management and local runtimes.
  • Excellent communication skills and ability to collaborate across teams.

Nice to have

  • Experience with Apple platforms or low-level OS runtimes and frameworks.
  • Experience with environment staging, telemetry, trace capture, or on-device AI/LLM runtimes.

Pay

$150,400 and $225,300 USD base salary

Tools

Swift, C++, Objective-C, Python, iOS, macOS, watchOS, visionOS

AI focus

Build evaluation infrastructure for agentic AI, including simulations of reasoning, tool use, on-screen awareness, and personal-context actions on-device.

Model-written summary · the original posting is authoritative

First seen Oct 15, 2026 · Last verified Nov 4, 2026 (UTC)