Multimodal AI Algorithm Expert-EMG / Interaction Perception, PICO

ByteDance
San Jose
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningEducation: mastersSkills: []

Work on multimodal interaction perception for XR, developing deep learning models that fuse surface electromyography (sEMG) signals with computer vision and IMU-based sensing. Build sEMG acquisition and preprocessing pipelines (denoising, feature extraction), design spatiotemporal fusion approaches (e.g., Transformer/LSTM/spatiotemporal CNNs), and improve robustness to sensor noise and interference to enhance generalization.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

Multimodal AI Algorithm Expert-EMG / Interaction Perception, PICO

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 30 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Work on multimodal interaction perception for XR, developing deep learning models that fuse surface electromyography (sEMG) signals with computer vision and IMU-based sensing. Build sEMG acquisition and preprocessing pipelines (denoising, feature extraction), design spatiotemporal fusion approaches (e.g., Transformer/LSTM/spatiotemporal CNNs), and improve robustness to sensor noise and interference to enhance generalization.
Location: San Jose
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Research and develop deep learning models at the intersection of sEMG, computer vision, and IMU technologies.
  • •Design and implement sEMG signal acquisition pipelines; optimize signal quality and perform denoising and feature extraction preprocessing.
  • •Explore spatiotemporal feature fusion methods (e.g., Transformer, LSTM, Spatiotemporal Convolutional Networks) for efficient multimodal fusion.
  • •Handle sensor noise and interference in diverse environments; optimize model performance and improve algorithm generalization.

Key Requirements

  • •Master’s degree or above in machine learning, signal processing, computer science, statistics, speech and language technology, or a related field.
  • •Strong deep learning fundamentals with experience training and deploying deep models; familiarity with fine-tuning end-to-end speech recognition frameworks (e.g., Conformer, RNN-T, LAS, CTC) and 2D/3D perception algorithms.
  • •Knowledge of sEMG signal acquisition and processing, including denoising (e.g., filtering) and time/frequency-domain feature extraction.
  • •Experience with digital signal processing techniques such as digital filtering, Fourier transforms, correlation analysis, and modulation.
  • •Preferred: experience modeling high-dimensional time-series data and/or publications in conferences (CVPR, ICCV, ECCV) and participation in competitions (e.g., Kaggle, COCO, ImageNet, ActivityNet).
Experience:Multimodal AIComputer visionSpeech recognitionSignal processingTime-series dataXR
Education:Master's
Tech Stack:Computer visionDeep learningSLAM3D reconstructionMulti-sensor fusionHandheld controllersBare-hand trackingEye-trackingXRSurface electromyography (sEMG)IMUSEMG signal acquisitionSignal denoisingFeature extractionTransformerLSTMSpatiotemporal Convolutional NetworksDigital signal processingDigital filteringFourier transforms

Company Brief

ByteDance
Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Headquarters: Beijing, China
Founded: 2012
WebsiteLinkedIn