Research Scientist Intern, PyTorch On-Device (PhD)

Job Description

About the Job: Research Scientist Intern, PyTorch On-Device (PhD) at Meta

This job posting is promoted by Lensa, a career site that helps job seekers find jobs in the US. Lensa is not a staffing firm or agency and does not hire directly for these roles. Instead, Lensa promotes jobs on behalf of its direct clients, recruitment ad agencies, and marketing partners, in this case, partnering with DirectEmployers to promote a job for META. Clicking “Apply Now” or “Read more” will redirect you to the official job board or employer site, where any collected information will be subject to their terms and privacy notice.

—

Summary & About the Team

Meta is seeking a Research Scientist Intern for its PyTorch On-Device team. PyTorch is Meta’s leading deep learning framework, crucial for fast, flexible AI/ML experimentation across the industry and underpinning all of Meta’s ML workloads (more details at https://pytorch.org/).

The PyTorch On-Device team is dedicated to bringing PyTorch to edge devices. This involves leveraging compilers, an optimized runtime, and unique mobile hardware (CPU, GPU, NPU, DSP) for both inference and training on devices.

Key areas of the team’s scope include:

• Developing ExecuTorch as the primary PyTorch solution for on-device AI.
• Partnering with Reality Labs to integrate and run AI on cutting-edge AR/VR hardware.
• Collaborating with the Meta family of apps to enable AI functionalities on iOS and Android platforms.
• Working closely with hardware vendors to develop high-performance AI kernels.
• Providing comprehensive solutions for on-device AI inference, feature stores, benchmarking, and model delivery.

This internship position is typically twelve (12) to twenty-four (24) weeks long, with various start dates available throughout the year.

—

Research Scientist Intern, PyTorch On-Device (PhD) Responsibilities

The successful intern will be expected to:

• Develop new or apply existing performance techniques specifically for on-device AI applications.
• Actively explore solutions such as quantization, sparsity, and model/software co-design to optimize on-device AI performance.
• Apply their knowledge and research findings to advance the state-of-the-art in on-device machine learning frameworks.
• Collaborate effectively with users and developers of PyTorch and ExecuTorch to enable and support new use cases, both internally within Meta and with external partners.

—

Minimum Qualifications

Candidates must meet the following criteria:

• Currently holds, or is actively in the process of obtaining, a PhD degree in Computer Science or a closely related STEM field.
• Possesses demonstrated experience in ML compilers, sparsity, quantization, kernel development, or similar relevant areas, particularly as applied to on-device and highly-constrained environments.
• Must be able to obtain and maintain work authorization in the country of employment at the time of hire and throughout the duration of employment.

—

Preferred Qualifications

Ideal candidates will also possess:

• Experience working on other AI/ML optimized runtime stacks.
• Proven experience with performance optimization of machine learning models for on-device inference.
• An intent to return to their degree program after the successful completion of the internship/co-op.
• A proven track record of achieving significant results, evidenced by grants, fellowships, patents, or first-authored publications at leading workshops or conferences (e.g., NeurIPS, MLSys, ASPLOS, PLDI, CGO, PACT, ICML, or similar).
• Experience working and communicating cross-functionally within a team environment.

—

Public Compensation

The compensation for this position ranges from $7,650/month to $12,134/month, in addition to benefits.

—

Industry

Internet

—

Equal Opportunity

Meta is proud to be an Equal Employment Opportunity and Affirmative Action employer. They are committed to non-discrimination based on race, religion, color, national origin, sex (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender, gender identity, gender expression, transgender status, sexual stereotypes, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics. Meta considers qualified applicants with criminal histories in accordance with applicable federal, state, and local law. Meta participates in the E-Verify program in certain locations, as required by law, and may leverage artificial intelligence and machine learning technologies in connection with employment applications.

Meta is dedicated to providing reasonable accommodations for candidates with disabilities throughout the recruiting process. If you require any assistance or accommodations due to a disability, please contact them at accommodations-ext@meta.com.

For any questions regarding this specific job posting, please contact support@lensa.com.