Vaibhav Agrawal
Doctoral Student at Werner Siemens Imaging Center
Tübingen, Baden-Württemberg, Germany
Summary
👤
Senior🎓
Top SchoolVaibhav Agrawal is a PhD-level ML researcher finishing at Tübingen (committee: Schölkopf, Bauer, Pichler) who specializes in data-efficient deep learning for small-cohort biomedical problems and generative models for protein design. He has delivered state-of-the-art, interpretable models that dramatically improve low-sample tumor-omics and malignancy prediction (e.g., a dictionary-learning CNN +36pp over fine-tuned ResNet-18 on 131 samples and an ensemble attribution pipeline reaching 83.4% on a 34-patient cohort). His work spans multi-modal PET–MRI fusion and large-scale 3D medical imaging (Nature Biomed Eng, JCI Insight), and he builds practical evaluation infrastructure—shipping the open TriFinger robot platform and the NeurIPS Real Robot Challenge cloud harness used by hundreds of teams. Currently developing non-autoregressive discrete diffusion over pretrained embeddings for activity-conditioned enzyme design with first validated designs expected Q3 2026, he’s strongest where scientific ML meets tight-data regimes, biomedical AI, or evaluation infrastructure. EU Blue Card eligible and open to research-scientist, ML-scientist, or research-engineer roles across DACH/EU/UK/CH from August 2026.
8 years of coding experience
1 year of employment as a software developer
BITS Pilani, Birla Institute of Technology and Science
Github Skills (50)
crossword7
robotics7
robot7
localization7
yarp7
stem7
generalization6
low-level6
webots6
simulation6
translation6
autonomous-robots5
robotics-simulation5
robot-simulator5
plot5
Programming languages (3)
Github contributions (5)
TheInfamousWayne/CheXNet
Feb 2019 - Feb 2022
CheXNet with localization
Contributions:6 commits, 1 PR, 5 pushes in 3 years
translationlocalizationchexnet
TheInfamousWayne/Self_Driving_Car
Feb 2018 - Apr 2022
Contributions:1 push, 1 branch in 4 years 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.