AIML - ML Engineer, Safety & Red Teaming

Apple - Pittsburgh, PA

Full-time

Pittsburgh, PA

Computer and Electronic Product Manufacturing

About the position

As an AIML - ML Engineer focused on Safety & Red Teaming at Apple, you will play a crucial role in the development and evaluation of generative AI applications. This position is part of the Apple HCMI group, where you will work on innovative projects that aim to enhance the safety, robustness, and interpretability of generative models. Your work will directly impact the future of Apple's products and the broader AI landscape. You will be tasked with developing models, tools, metrics, and datasets that assess and evaluate the safety of generative models throughout their deployment lifecycle. This includes creating methodologies to interpret and explain failures in language and diffusion models, as well as building and maintaining human annotation and red teaming pipelines to assess the quality and risk associated with various Apple products. In this role, you will prototype, implement, and evaluate new machine learning models and algorithms specifically designed for red teaming large language models (LLMs). Your contributions will be vital in ensuring that Apple's generative models are not only effective but also safe and reliable for end-users. You will collaborate with a diverse team of scientists and engineers, leveraging your expertise in machine learning to tackle complex challenges and drive innovation in generative AI.

Responsibilities

• Develop models, tools, metrics, and datasets for assessing and evaluating the safety of generative models over the model deployment lifecycle.
• Develop models and tools to interpret and explain failures in language and diffusion models.
• Build and maintain human annotation and red teaming pipelines to assess quality and risk of various Apple products.
• Prototype, implement, and evaluate new ML models and algorithms for red teaming LLMs.

Requirements

• Strong engineering skills and experience in writing production-quality code in Python, Swift, or other programming languages.
• Background in generative models, natural language processing, LLMs, or diffusion models.
• Experience with failure analysis, quality engineering, or robustness analysis for AI/ML based features.
• Experience working with crowd-based annotations and human evaluations.
• Experience working on explainability and interpretation of AI/ML models.

Nice-to-haves

• BS, MS or PhD in Computer Science, Machine Learning, or related fields or an equivalent qualification acquired through other avenues.
• Proven track record of contributing to diverse teams in a collaborative environment.