Meta’s Reality Labs Research (RL-R) is looking to solve complex challenges in behavioral inference from sparse information using multimodal, egocentric data and cutting-edge machine learning to deliver robust, efficient models that serve everyone. The goal is to provide core building blocks to unlock intuitive and helpful Wearable AI, empowering everyone to harness the superpowers of this emerging technology in their daily lives.
Requirements
- Proven track record of solving complex challenges with multimodal ML as demonstrated through grants, fellowships, patents, or publications in top journals or at conferences like CVPR, NeurIPS, CHI, or equivalent.
- 2+ years of documented experience with multimodal sensing platforms, data collection, multimodal data processing and analysis.
- 2+ years of coding experience documented in publications or open source (e.g., GitHub) repositories (such as Python, C++, PyTorch, etc.).
- Experience with Large Language Models.
- Experience with Multimodal Deep Learning approaches and research.
- PhD degree in Behavioral Science, Computer Science or related field plus 3+ years experience with biosignals, behavioral signals, or egocentric data from wearable sensors.
- Experience working in Wearables, Augmented Reality/Virtual Reality.
Responsibilities
- Develop novel, state-of-the-art algorithms for wearables that incorporate social behavior dynamics and multimodal sensing platforms.
- Design and implement data collection strategies, benchmarks, and metrics to validate and improve model efficiency, scalability, and stability.
- Develop AI algorithms that can infer human behavior patterns from wearable devices.
- Work with multiple egocentric sensor modalities to advance our understanding of human behavior in various contexts.
- Characterize human behavior in-the-wild to derive behavioral signals for user states in the form of quantitative insights from ethnographic observations.
- Translate results of human data collection into datasets that can be effectively leveraged by ML tools and language readily interpretable by foundational models.
- Create tools, infrastructure, and documentation to accelerate research.
Other
- Documented understanding of social behavior dynamics, including expertise in psychology and human-human interaction.
- 2+ years of research scientist (post-PhD) experience with designing field experiments, data campaigns, and observation skills for human behavior.
- Collaborate with researchers and engineers across broad disciplines through all stages of project development.
- Contribute to research that can eventually be applied to Meta products and services.
- Learn constantly, dive into new areas with unfamiliar technologies, and embrace the ambiguity of Augmented Reality/Virtual Reality problem solving.
