Senior Data Scientist - Evaluation & LLM Judge Innovation

Apple; Cupertino (CA); On-site; USD 150,000 - 278,000; Full time

Benefits offered by this job

Medical and dental coverage

Retirement benefits

Employee stock plans

Bonuses or commissions (if eligible)

Relocation (if eligible)

Discounted products and services

Educational expense reimbursement

Job summary

Apple’s Evaluation team focuses on measurable product impact, helping improve Siri and Apple Intelligence. In this role, you’ll develop evaluation methods that translate into everyday technology for product engineering, using advanced analytics on large datasets and LLM-based judging to support better decisions across Apple products.

Location: Cupertino, CA onsite. Base pay range USD 150,400 to 277,600 per year as part of total compensation.

Qualifications

• Advanced degree in a quantitative field such as Statistics, OR, Bioinformatics, Economics, CS or related.
• Proficiency in data science, machine learning, analytics and statistical analysis.
• Experience planning, running and interpreting experiments focused on data quality, evaluation and risk.
• Strong programming skills with SQL/Spark and Python/R/Scala or similar.
• Ability to translate business questions into data-driven analysis.
• Clear communication to data scientists, engineers and business partners on complex topics.

Responsibilities

• Research and develop evaluation methods to improve the quality of Apple user facing products, including Siri and Apple Intelligence.
• Partner with evaluation and experimentation teams to productionize methodologies for product engineering use.
• Work with large data sets to support accurate evaluation and insight generation.
• Solve non-routine analysis problems using advanced analytical methods, including prompt engineering and using LLMs as judges.
• Lead analysis covering data collection and quality control, requirements, processing and presentations.
• Prototype analysis pipelines iteratively to deliver scalable insights.
• Develop knowledge of product data structures and metrics, advocating for changes in product development.
• Collaborate with product engineering on core ML algorithms and user experience evaluations.

Skills

Data science, ML, analytics

Strong communication

Learn new technologies

Education

Advanced degree in a quantitative field

Tools

SQL

Spark

Python

R

Scala

LLMs

Prompt engineering

Job description

Apple’s Evaluation team focuses on measurable product impact, helping improve Siri and Apple Intelligence. In this role, you’ll develop evaluation methods that translate into everyday technology for product engineering, using advanced analytics on large datasets and LLM-based judging to support better decisions across Apple products.

Location: Cupertino, CA onsite. Base pay range USD 150,400 to 277,600 per year as part of total compensation.