Soumya Barikeri is a Senior Data Scientist specializing in NLP with seven years in IT and over three years focused on production-grade language and speech solutions. Based in Bengaluru, she has built end-to-end systems—from a tourism question-answering chatbot over RDF and vector search to domain-tuned GPT-2 autocompletion and low-resource medical ASR—leveraging multi-GPU cloud training and careful evaluation frameworks. Her work blends research and engineering: she fine-tuned multilingual transformers and GNNs for knowledge graph enrichment, improved next-word accuracy by 10% and raised F1 scores through unsupervised domain adaptation. Comfortable spanning retrieval, generation, speech and hybrid classifier designs, she also tackles practical issues like sequence-length limits and feature fusion for real-world web data. Soumya’s background in electronics and a Data Science master’s informs a pragmatic approach to model robustness and deployment. An inquisitive engineer, she repeatedly demonstrates measurable gains by combining rigorous experimentation with production constraints.
7 years of coding experience
Master's degree, Data Science, Master's degree, Data Science at University of Mannheim
Bachelor’s Degree, Electronics and Communication engineering, Bachelor’s Degree, Electronics and Communication engineering at RV College Of Engineering
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.