Research Scientist, HW/SW Co-Design (PhD)

Job Title

Research Scientist, HW/SW Co-Design (PhD)

Role Summary

Join Meta's AI and Systems CoDesign Group to perform research and development at the intersection of generative AI workload analysis, model enablement, and hardware/software co-design for Meta's custom datacenter accelerators. The role spans ideation, prototyping, performance modeling, and collaborating with hardware architects and compiler teams to move results toward production.

Experience Level

Mid-level research scientist; requires demonstrated research experience and technical contributions in systems, hardware-aware ML, or related areas. Specific years of experience are not stated.

Responsibilities

Core responsibilities focus on co-design, performance analysis, and cross-team execution.

• Lead hardware-software co-design efforts targeting programmability, performance, and power efficiency for Meta's AI accelerators.
• Analyze AI workloads and integrate findings into the accelerator roadmap and system design choices.
• Build and use system performance models and simulators to evaluate architecture and infrastructure options.
• Co-optimize deep learning kernels and primitives with hardware architects and compiler teams for PPA (performance, power, area).
• Design and implement frameworks and tooling for comparative analysis across system architectures.
• Drive cross-functional projects to deliver technical milestones from prototype to productization.
• Publish and present peer-reviewed research at leading conferences in ML and systems.

Requirements

Minimum technical and practical qualifications required for successful performance in this role.

Must-have:

• Theoretical and practical experience with AI models such as CNNs, Transformers, LLMs, or diffusion models.
• Research experience in hardware-aware model enablement, performance modeling of AI systems, or accelerator/silicon architectures.
• System-level performance analysis, profiling, and benchmarking experience for AI workloads.
• Hands-on experience with end-to-end AI hardware architecture or on-device mapping algorithm development, including logic, architecture, and optimizations for performance, power, and area.
• Proficiency in Python and experience with at least one major AI framework (e.g., PyTorch, TensorFlow).
• Track record of publishing in peer-reviewed venues and communicating technical results to both technical and non-technical stakeholders.
• Must obtain and maintain work authorization in the country of employment at time of hire.

Nice-to-have / Preferred:

• Experience with state-of-the-art performance modeling infrastructure and AI model performance projection.
• Evidence of significant research impact such as grants, fellowships, patents, or first-authored publications at leading conferences.
• Experience deploying AI agents and techniques for model efficiency.
• Familiarity with low-level programming for specialized hardware (CUDA, HIP, Triton) or hardware description languages (HDL).
• Experience influencing custom silicon architecture or co-designing HW/SW interfaces.
• Proven ability to work cross-functionally across engineering teams.

Education Requirements

PhD in Computer Science, Electrical Engineering, Applied Mathematics, or a related technical field is listed (candidates may be in-progress but degree must be completed prior to joining). The posting also references a Bachelor's degree in Computer Science, Computer Engineering, or a related field as an educational baseline in other qualification statements. Equivalent practical experience is accepted as an alternative where noted.

About the Company

Company: Meta Platforms

Headquarters: Menlo Park, California, United States

American technology company that develops social networking products (Facebook, Instagram, WhatsApp) and invests in virtual/augmented reality hardware and software through Reality Labs, focusing on connectivity, advertising, and immersive computing experiences.