Backend Engineer, Measurement - Evaluation

Would you like a chance to create a significant impact, working alongside world-class experts and using innovative technologies to push the boundaries of whats possible? At Apple, we believe in creating technology that enriches lives and empowers creativity. Youll play a pivotal role in developing Apple Intelligence, driving the next generation of groundbreaking products across all Apple platforms.

The team is a dynamic group working at the intersection of product engineering, ML research, and Data Science. We are looking for an engineer with a strong software development background to build the backend systems, APIs, and logic that drive our internal evaluation platform.

In this role, you will move beyond operations and deployment to focus on the architecture and implementation of complex software solutions. You will translate the intricate requirements of LLM evaluation into robust, scalable code. You will leverage your understanding of Machine Learning to design systems that can intelligently interact with models, ensuring that Apples AI products meet the highest standards of quality.

Responsibilities:

• Software Architecture & Design: Architect and implement high-performance, scalable software services and libraries for model evaluation.
• System Development: Write clean, maintainable, and efficient code (Python, C++, or Go) to power the evaluation engine, focusing on algorithmic efficiency and data structure optimization.
• ML Integration: Collaborate with researchers to understand model behaviors and translate complex ML concepts into reliable engineering specifications and software features.
• API & Tooling: Design and build internal APIs and developer tools that allow other teams to seamlessly interact with evaluation logic.
• Cross-Functional Collaboration: Partner with data scientists and product managers to define technical requirements and turn experimental methodologies into production-grade software features.
• Innovation: Continuously seek ways to enhance evaluation frameworks, adopting best practices and integrating the latest advancements in technology.

Requirements:

• 4+ years of professional experience in software engineering, with a strong focus on backend development and system design.
• Proficiency in at least one modern programming language (e.g., Python, C++, Swift, Go, or Java) with a deep understanding of writing efficient, production-ready code.
• Solid understanding of computer science fundamentals, including algorithms, data structures, and software design patterns.
• Experience designing and building RESTful APIs or gRPC services.
• Ability to communicate complex technical concepts effectively to diverse audiences, including non-engineering stakeholders.
• Bachelors degree in Computer Science, Engineering, or a related field.

Preferred Qualifications:

• ML Implementation: Experience using ML frameworks (PyTorch, TensorFlow) or integrating LLMs into software applications (using libraries like Hugging Face or LangChain).
• Experience with vector databases and search technologies.
• Background in developing evaluation metrics or testing frameworks for software or data systems.
• Familiarity with CI/CD pipelines, containerization (Docker, Kubernetes), and infrastructure as code.
• Solid understanding of machine learning algorithms, model evaluation metrics, and data processing pipelines.
• Knowledge of distributed computing patterns.
• Masters or Ph.D. in Computer Science or a related field.