Computer Vision Silicon Architect
Facebook AR/VR focuses on delivering Facebook's vision through Augmented Reality (AR) and Virtual Reality (VR). The compute performance and power efficiency requirements of Virtual and Augmented Reality require custom silicon. Facebook Silicon team is driving the state of the art forward with breakthrough work in computer vision, machine learning, mixed reality, graphics, displays, sensors, and new ways to map the human body. Our chips will enable AR and VR devices where our real and virtual world will mix and match throughout the day. We believe the only way to achieve our goals is to look at the entire stack, from transistor, through architecture, to firmware, and algorithms.
We are seeking a Computer Vision Silicon Architect who is excited about introducing ground breaking capabilities in the fields of computer vision, machine-learning and imaging, through the development of specialized HW components, and the adaptation of algorithms to HW implementation. The successful candidate will be required to architect custom ICs/ASICs in close collaboration with the groups developing the algorithms, system software and SoCs.
This is a full-time position based in our Menlo Park campus, CA.
- Study state of the art algorithms in the field of computer vision, machine learning and imaging, come up with appropriate SW-HW partitioning, provide architecture and specifications for HW implementation
- Come up with new algorithms, or adaptations to existing algorithms, that will enable new ground-breaking capabilities through HW implementation
- Implement and test architecture and specifications, to assure correctness and consistency with the algorithm
- Support all phases of Silicon SoC development from early definition on through architecture & specification, design, verification, prototyping and SOC bring-up
- Collaborate closely with algorithm developers, SoC architects and designers to support the realization of the necessary hardware to enable innovative AR/VR experiences
- Contribute to execution of our silicon technology and compute roadmap to make beyond state-of-the-art advances in performance, power consumption and form factor
- Assess and recommend emerging technologies through close partnership with external, industry leading suppliers
- 3+ years of experience in digital IC architecture or design supporting computer vision, machine learning or image processing use cases
- Knowledge in the field of computer vision, machine learning and image processing
- Experience with methods for partitioning a solution across hardware and software, and other multi-disciplinary boundaries in a system solution
- Experience with C++ code and hands-on coding for the purpose of developing and testing HW architecture
- Experience with fixed-point arithmetic
- Experience evaluating architectural tradeoffs in speed, performance, power, area
- Experience working in the consumer electronics field
- Bachelor's EE/CS or equivalent
- Experience in developing algorithms for computer vision/machine learning/image processing use cases
- Proficiency in C/C++ programming
- Experience in advanced ASIC/SoC design methodologies
- Experience with top down high-level-model to HW mapping
- Master's or PhD in EE/CS
- Knowledge of industry trends and disruptive technologies
- Results oriented, self-motivated, proactive with demonstrated creative & critical thinking skills
- Ability to operate autonomously, with only high-level direction
Meet Some of Facebook's Employees
Yumeng T.Research Scientist
Yumeng spends her days working with machine learning models for search products and completing product-level coding projects.
Back to top