Job Description
Facebook's mission is to give people the power to build community and bring the world closer together. Through our family of apps and services, we're building a different kind of company that connects billions of people around the world, gives them ways to share what matters most to them, and helps bring people closer together. Whether we're creating new products or helping a small business expand its reach, people at Facebook are builders at heart. Our global teams are constantly iterating, solving problems, and working together to empower people around the world to build community and connect in meaningful ways. Together, we can help people build stronger communities - we're just getting started.Facebook Reality Labs focuses on delivering Facebook's vision through Virtual Reality (VR) and Augmented Reality (AR). Enabling compelling user experiences on Virtual and Augmented Reality devices requires innovation and co-design across all layers of stack from novel algorithms to custom silicon. Facebook Reality Labs is driving the state-of-the-art forward with breakthrough work in computer vision, speech, virtual assistant, machine learning, mixed reality, graphics, displays, sensors, and new ways to map the human body among many others.Our team, On-device AI Assistant, focuses on developing software stack to deploy efficient Deep Learning solutions to enable compelling user experiences on Facebook AR products -- with the long term of enabling an always-on, proactive FB assistant on-device. We are seeking a Research Engineer with experience in optimizing machine learning kernels, compiler passes or low-level programming to manage runtime on Deep Learning Accelerators/DSPs. The ideal candidate will have hands-on experience in optimizing and/or deploying machine learning workloads on different hardware backends such as DSP/GPU/DL Accelerators. In this position, you will get exposure to the full stack from user experiences, algorithms down to hardware execution blocks. You will work with the domain experts in natural language and other assistant-related aspects of Virtual/Augmented Reality to understand the challenges and build state-of-the-art solutions to tackle them and then work with the software/hardware team to deploy these solutions on-device.
Responsibilities
- Implement optimized machine learning kernels for DSPs and/or custom accelerators.
- Implement compiler passes, memory allocation/movement passes, or runtime components to deploy models on custom backends.
- Collaborate with researchers and hardware engineers to develop tradeoff curves for resources/constraints such as memory, latency, energy.
- Communicate experimental results and recommendations clearly, both within the group as well as to the cross-functional groups.
- Currently has, or is in the process of obtaining, a Master's Degree in Computer Science or related discipline.
- Demonstrated experience in optimizing/deploying machine learning models on custom backends such as DSPs/GPUs/DL Accelerators.
- 3+ years experience in C/C++/Python programming.
- Knowledge of algorithm design, performance profiling and debugging.
- Background in computer architecture.
- Interpersonal experience: cross-group and cross-culture collaboration.
- Must obtain work authorization in country of employment at the time of hire, and maintain ongoing work authorization during employment.
- Extensive experience in optimizing for execution constraints such as memory capacity, memory latency etc.
- Familiarity with Deep Learning models for Audio/Speech/Language.