Human-Centered AI ML Engineer: Evaluations & Insights

Apple, Inc.; Seattle (WA); On-site; USD 142,000 - 263,000; Full time

Benefits offered by this job

Medical & dental coverage

Retirement benefits

Employee stock programs

Stock Purchase Plan

Tuition reimbursement

Relocation assistance

Job summary

Apple, Inc. in Seattle, WA is seeking a Machine Learning Engineer focused on Evaluation & Insights for the Human-Centered AI team. You will bridge human perception and model performance, architect evaluation frameworks, and translate qualitative failures into training signals.

Collaborate with Data Scientists, Researchers, and Engineers to ensure reliable, safe AI experiences across Apple platforms. Strong ML engineering and evaluation skills required.

Qualifications

• 5+ years in ML Engineering or applied research.
• Strong Python and modern DL ecosystems (PyTorch/JAX).
• Experience building scalable ML inference and evaluation workflows.
• Ability to interpret unstructured model outputs and guide engineering.
• Hands-on with LLMs, multimodal models, or NLP systems.
• Familiar with AI quality metrics, RLHF/DPO, and LLM-as-a-judge.
• Experience with ML tooling like MLflow or Weights & Biases.

Responsibilities

• Lead rigorous evaluations for LLMs and multimodal models.
• Develop evaluation frameworks and scoring for quality metrics.
• Translate failure modes into actionable data adjustments.
• Collaborate with teams to improve model behavior via prompts and RAG.
• Build scalable MLOps and distributed evaluation pipelines.
• Define human-centric metrics and interpretable signals.
• Create automated evaluation pipelines using LLMs.
• Partner with researchers, software engineers, and product managers.

Skills

Python

ML Frameworks

Model Evaluation

NLP/LLM

Data Analysis

RLHF/DPO

Education

Bachelor's or Master’s in CS/ML/AI

Tools

MLflow

Weights & Biases

HuggingFace

Ray

vLLM

Vector DBs

Job description

Apple, Inc. in Seattle, WA is seeking a Machine Learning Engineer focused on Evaluation & Insights for the Human-Centered AI team. You will bridge human perception and model performance, architect evaluation frameworks, and translate qualitative failures into training signals.

Collaborate with Data Scientists, Researchers, and Engineers to ensure reliable, safe AI experiences across Apple platforms. Strong ML engineering and evaluation skills required.