Apple's Siri AI Quality Engineering team is looking to solve the problem of ensuring high-quality, privacy-focused conversational assistant technologies for large-scale systems and new client devices. This involves validating the instrumentation of AI assistant products at scale with a specific focus on user privacy, creating tools and frameworks for privacy evaluation, and ensuring trustworthy measurement of AI products.
Requirements
- 5+ years of proven experience designing, implementing, and optimizing large-scale data-driven platforms and frameworks, APIs, services, and tools.
- Strong programming skills in Swift, with Python experience being highly valued.
- Experience building dashboards and analytics solutions using tools like Tableau, Grafana, Superset, or Splunk to visualize KPIs and monitor data quality.
- Deep understanding about large scale data validation platforms with focus on privacy.
- Experience building and deploying applications with Kubernetes.
- Knowledge of statistics-based evaluation approaches, ML training pipelines, and techniques for enhancing the accuracy of ML systems.
- Thorough understanding of backend architecture, privacy-preserving data practices, and large-scale system design.
Responsibilities
- Designing, building, and evolving the evaluation environments and fundamental assertions to validate the instrumentation of our AI assistant products at scale with a focus on user privacy.
- Create tools and frameworks for instrumentation and privacy evaluation, ensuring that our AI products meet their privacy promises and are instrumented for trustworthy measurement.
- Collaborating closely with data and product engineering teams to provide evaluation methodologies and automation frameworks within a micro-services architecture.
- Designing, implementing, and optimizing large-scale data-driven platforms and frameworks, APIs, services, and tools.
- Building dashboards and analytics solutions using tools like Tableau, Grafana, Superset, or Splunk to visualize KPIs and monitor data quality.
- Experience building and deploying applications with Kubernetes.
- Experience in designing and building scalable ETL pipelines, high-performance data stores, and automated workflows.
Other
- Demonstrated success in collaborating cross-functionally with engineering, machine learning, and data science teams to solve sophisticated challenges.
- Strong attention to detail and proven track record of delving into data, uncovering hidden patterns, and conducting comprehensive error/deviation analysis.
- BS/MS or equivalent experience in Computer Science, Engineering, or a related field.
