Machine Learning - Data Scientist Lead

Do you have a passion for computer vision and deep learning? Are you excited by the latest advances in multimodal models? The Video Engineering Data Analytics and Quality group is looking for a technical lead with deep expertise in evaluating machine learning and deep learning models, including foundation models and multimodal systems.

Description

In this role, you will design robust evaluation frameworks, mentor a team of engineers and scientists, and drive alignment across Apple's research, engineering, and product teams. You will combine strong analytical thinking, Python expertise, and a deep understanding of statistical evaluation and data quality. You will also help set the technical direction for how we measure and improve the quality of some of Apple's most exciting AI experiences.","responsibilities":"Lead and mentor a small team of ML evaluation engineers and data scientists, providing technical guidance, feedback, and code reviews.

Define team-level evaluation standards and best practices that other teams across Apple can adopt.

Own the technical roadmap for evaluation infrastructure, from planning through execution.

Onboard and ramp up new team members on tools, datasets, and workflows.

Design and implement scalable evaluation frameworks for machine learning and deep learning models.

Develop robust methodologies to assess the performance of foundation models (such as LLMs and vision-language models) across diverse tasks.

Leverage LLMs as judges to perform subjective and open-ended model evaluations, for example in summarization, reasoning, or multimodal generation tasks.

Create, curate, and manage evaluation datasets and benchmarks.

Drive cross-functional alignment by partnering with product managers, research leads, and engineering managers to prioritize evaluation goals.

Collaborate with ML engineers, data scientists, and ML infrastructure engineers to deliver great user experiences.

Communicate findings clearly through dashboards, presentations, and technical documentation.

Influence without authority across teams with different goals and priorities.

Conduct failure analysis and uncover edge cases to improve model robustness.

Contribute to internal tools and infrastructure to automate and scale evaluation processes.

Write clear technical reports and present findings to both technical and non-technical audiences.

Preferred Qualifications

M.S. or Ph.D. in Computer Science, Statistics, Machine Learning, or a related field.

Prior experience managing or tech-leading a team of two or more engineers or scientists.

Experience with open-source evaluation tools such as OpenEval, ELO-based ranking, or LLM-as-a-Judge frameworks.

Familiarity with prompt engineering, few-shot, or zero-shot evaluation techniques.

Experience evaluating generative models, such as text or image generation systems.

Prior contributions to ML benchmarks or public evaluations.

Comfort with giving and receiving feedback in a collaborative, fast-moving environment.

Strong communication and documentation skills, with the ability to write technical reports and present to non-technical audiences.

Minimum Qualifications