AI Evaluation & Benchmarking Lead

Apple Inc.; Cambridge; On-site; GBP 120,000 - 170,000; Full time

Job summary

Apple Inc. in Cambridge, England is seeking a Senior Manager to lead evaluation development and data science for Siri AI, shaping state-of-the-art agentic evaluation across iOS, iPadOS, macOS, watchOS and visionOS.

You will manage teams, drive high-impact initiatives, and collaborate with Finance and International partners to plan budgets and resourcing. This role emphasizes privacy-first design and real-world impact across platforms.

Qualifications

• Agentic coding proficiency for data science, data collection and visualization.
• Strong understanding of metrics, crowd science, data collection, annotation analysis, statistics.
• Ability to work independently and cross-functionally with partner team reporting systems.
• Excellent communication skills and the ability to thrive in a highly collaborative work environment.

Responsibilities

• Design and execute data collection processes using humans in the loop.
• Lead annotation efforts for various languages and devices.
• Plan and manage annotator resourcing budgets with Finance, Annotation Ops, and International team partners.
• Track and improve quality of human judgements through training materials and review processes.
• Collaborate with engineering teams to build tooling for managing and browsing rich datasets.

Skills

Agentic coding

Metrics understanding

Crowd science

Data collection

Annotation analysis

Statistics

Independent work

Cross-functional collaboration

Communication skills

Tools

Python

Data visualization tools

Job description

Apple Inc. in Cambridge, England is seeking a Senior Manager to lead evaluation development and data science for Siri AI, shaping state-of-the-art agentic evaluation across iOS, iPadOS, macOS, watchOS and visionOS.

You will manage teams, drive high-impact initiatives, and collaborate with Finance and International partners to plan budgets and resourcing. This role emphasizes privacy-first design and real-world impact across platforms.