ML Evaluation Engineer — Adversarial Testing at Scale

Apple, Inc. in Seattle, WA is seeking an ML Engineer focused on automated evaluation and adversarial design. You will design, build, and scale evaluation systems for AI features, including multi-turn conversations and agent workflows.

The role emphasizes adversarial test suites, stress testing, and alignment between automated and human evaluation. Strong Python and ML framework experience is required, with a track record of guiding evaluation across features.