Machine Learning Manager, FM Runtime

As a ML Engineering Manager for Foundation Model Runtime, you will manage and lead top flight ML engineers to deliver high performance inference solutions for generative AI features that power tentpole Apple features. You will work across organizations to connect product teams, model teams, FM services, cloud infrastructure, and your own team to deliver carefully engineered, high performance solutions aligned with critical milestones. You will also guide the team to architect for maximum leverage in the ML space, helping the team adapt the latest innovations in generative AI inference.

Description

Your role as Engineering Manager will provide support and leadership to incredible ML inference talent to deliver state of the art inference features and performance across Apple. This role offers the opportunity to turn cutting edge inference techniques into carefully crafted engineering solutions that will power both experimentation and production serving of generative AI models across multiple modalities. You will be gauging impact and aligning engineering resources to tackle new hardware and environments, meeting latency, throughput, and quality targets. You will develop technical talent and leadership in your team, and grow your team to meet new inference challenges. You will work cross functionally to set grounded expectations and provide key data that influence AI product development decisions and hardware investments.","responsibilities":"Balance both technical execution and the long-term vision for the team

Collaborate effectively with partner and product teams to define goals, set expectations, and shape roadmaps.

Provide both technical and career mentorship, empowering your team to succeed.

Strong interpersonal skills are essential for communicating technical complexities clearly to engineering partners, product management teams, and executives across Apple.

Preferred Qualifications

Masters degree in AI, Machine Learning, Computer Science, Mathematics

Strong understanding of AI model architecture, including transformers and vision models

Experience in model profiling and performance, evaluation, and roofline analysis

Minimum Qualifications

Bachelor's degree or equivalent experience in AI, ML, Mathematics, Computer Science, or a related field.

5+ years of experience applying and leading teams that productionize ML models or apply ML inference in areas of search, knowledge, or other AI adjacent areas.

3+ years of experience managing ML teams and leading ML development.

Experience in management of AI accelerator hardware and software infrastructure, ML performance analysis and tuning, transformer architecture and modeling, and algorithms