AI Engineer — Agentic Systems & Vision Evaluation

Apple Inc.; Sunnyvale (CA); On-site; USD 150,000 - 278,000; Full time

Benefits offered by this job

Stock programs

Education reimbursement

Comprehensive health benefits

Job summary

Apple Inc. in Sunnyvale, California, seeks an AI Engineer specializing in algorithm evaluation and agentic systems for advanced computer vision and video understanding.

The role centers on rigorous testing, benchmarking, and building autonomous multi‑modal workflows bridging experimentation with production. You will lead evaluation pipelines, analyze failures, and collaborate with model training teams to steer iterations.

Qualifications

• MS and a minimum of 3 years relevant industry experience.
• 3+ years of applied experience in Machine Learning, Computer Vision, or AI System Evaluation.
• Solid ML foundation: probability, statistics, data distributions, and model bias/variance.
• Engineering with Python and PyTorch for running inference and building evaluation pipelines.

Responsibilities

• Algorithm Evaluation & Benchmarking: design, build, and scale comprehensive evaluation pipelines.
• Deep Failure Analysis: identify root causes of visual hallucinations, temporal inconsistencies, and edge-case failures.
• Agentic Architecture: build, deploy, and evaluate agentic workflows that use vision models to solve multi-step problems.
• Golden Data Curation: curate high-quality, schematized datasets and ground-truth benchmarks for multi-modal evaluation.
• Cross‑Functional Collaboration: work with core model training teams to provide actionable metrics.

Skills

Machine Learning

Computer Vision

AI System Evaluation

Python

PyTorch

Evaluation Pipelines

Education

MS degree in a relevant field

Job description

Apple Inc. in Sunnyvale, California, seeks an AI Engineer specializing in algorithm evaluation and agentic systems for advanced computer vision and video understanding.

The role centers on rigorous testing, benchmarking, and building autonomous multi‑modal workflows bridging experimentation with production. You will lead evaluation pipelines, analyze failures, and collaborate with model training teams to steer iterations.