Meta AR/VR Job | Wearables Algorithms Research Engineer | Oculus
Job（岗位）: Wearables Algorithms Research Engineer | Oculus
Type（岗位类型）: Engineering | Machine Learning, Research
Citys（岗位城市）: Remote, US | Burlingame, CA
Date（发布日期）: 2022-2-28
Summary（岗位介绍）
At Reality Labs Research (RL-R), our goal is to explore, innovate and design novel interfaces and hardware subsystems for the next generation of virtual, augmented, and mixed reality experiences.
Our aim is to unleash human potential by erasing the bottlenecks between intent and action. The key to this work is in the development of robust, adaptive algorithms and systems that can seamlessly power the decoding of wearable biometrics and drive powerful adaptive XR interfaces.
As a Research Engineer, you will focus on developing novel, robust, and real-time multi-sensor processing algorithms for wrist-wearables. Your work will involve novel techniques around self-supervised learning, robust decoding of biometric signals, confounder mitigations, and state-estimation/sensor-fusion techniques for stringing an entire ultra-low-friction (ULF) interactive system together. Lastly, you will also be responsible for the full-stack integration of your work onto our real-time SDKs and systems for the creation of compelling demonstrations of this technology.
Our research lies at the intersection of signal processing, machine learning, and human-computer interaction (HCI), and is both state-of-the-art research but also applied, practical, and concrete. You will work with world-leading collaborators, researchers, and mentors in the AR/VR, machine learning, neuroscience, AI, and HCI fields.
Qualifications（岗位要求）
Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta.
MS degree in signal processing, computer vision, machine learning, state-estimation, robotics, or equivalent.
3+ years of academic/industry experience around multi-channel time-series signal processing, fusion, and algorithms design.
3+ years of experience with scientific programming languages such as Python, PyTorch or C++.
Interpersonal skills: cross-group collaboration and cross-culture collaboration.
Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment.
Description（岗位职责）
Plan, execute, code, and integrate (i.e., full-stack development) of cutting-edge research and design (R&D) of novel adaptive algorithms for a variety of different sensory modalities. This includes classification, fusion, confounder mitigation, and robust real-time gesture recognition algorithms and systems that yield seamless interactions.
Rapid prototyping of proof-of-concepts for various DNN, fusion and signal processing algorithms. This includes working deeply in our code base, and not shying away from integration responsibilities. Work closely with our data collection team to articulate and assist in data collection protocol design, labeling protocols, etc. You will also be expected to be able to assist in giving valuable feedback and guidance to our tooling team.
Design algorithms that lend themselves towards being sample efficient, easily tunable, and adaptive enough to work across multiple users and multiple use-cases with minimal re-training. Typical modalities can include, but are not limited to, EMG, IMU, Imaging sensors, PPG, etc.
Clearly communicate, present, and articulate algorithm and system designs to the team and beyond.
Additional Requirements（额外要求）
PhD degree in signal processing, computer vision, machine learning, state-estimation, robotics, or equivalent.
5+ years of industry experience around multi-channel time-series fusion and algorithms design.
5+ years of experience with scientific programming languages such as Python, PyTorch and/or C++.
Proven track record in the design of novel and fieldable algorithms that have been deployed in the real-world and in real-time (e.g., Wireless, RADAR, SONAR, Biometrics such as EMG or EEG signal processing stacks, including beamforming or fusion techniques).
Experience with self-supervised learning, state estimation and/or sensor-fusion techniques and natural language processing (NLP).
Experience with biometric modeling for real-time interactive scenarios (e.g., gesture recognition, task inference).
