
Postdoctoral Researcher - Audio Processing & Reconstruction 3D
Paris
Wigi highlights
4+ years, currently working as Mid-level Postdoctoral Researcher
Pioneered a cross-modal NeRF and acoustic field framework
Developed multimodal generative AI models with state-of-the-art audio performance
Created diffusion models for audio generation based on multimodal scene context (3D & audio), enabling few-shot generalization; engineered solutions using 3D modalities (voxels, point cloud) and advanced audio signal processing techniques to improve model accuracy in complex environments.
In a separate role, conceived and implemented neural networks (UNet, GAN, LSTM, Student-Teacher, lightweight model) to reconstruct scenes and depth from collected data, and reconstructed depth from mono and stereo images to obtain pseudo ground truth (stereovision, mono-to-depth, Structure-from-Motion).
Open to offers
Open to new opportunities
Skills
Work experience
Unlocks when they connect with you.
- certifications· 5
- education· 6
Similar available Data Scientists
View all- Data Science Researcher (C++, Python) · Wrocław, Poland · 1 Yr Exp · Remote · $3,200/mo
- Founder & Data Science Lead · Maidstone, UK · 8 Yrs Exp · Remote · $7,000/mo
- Data Scientist | Data Modeling & Critical Thinking · Athens, Greece · 5 Yrs Exp · Remote · $3,700/mo
- Lead Data Scientist - Atomic-Scale Imaging Optimization · Madrid, Spain · 7 Yrs Exp · Hybrid · $3,800/mo
- Data Scientist / Data Engineer (MongoDB, Pandas) · Lisbon, Portugal · 5 Yrs Exp · Remote · $3,900/mo