Sai Jayanthi
Applied Scientist II at Amazon
United States
Summary
👤
Senior🎓
Top SchoolSai Jayanthi is an Applied Scientist II at Amazon AGI with eight years of experience building production-ready ML and deep learning systems for text and speech. He has a strong research-to-production track record spanning conversational AI (notably improving entity resolution in Cisco’s open-source MindMeld), zero-shot intent classification, knowledge-graph reasoning, and multimodal recommendation engines. His background combines an MS from Carnegie Mellon with hands-on roles at Cisco, Samsung Research, and internships that produced novel audio alignment and air-quality models. Sai frequently bridges research and engineering—shipping distilled embedder-based resolvers, refactoring complex modules, and exposing models as REST APIs for deployment. He brings both academic rigor and practical product sensibility, often tackling low-data and cross-lingual challenges in real-world systems. Colleagues value his ability to translate advanced models into maintainable, tested components that scale in production.
8 years of coding experience
4 years of employment as a software developer
Matriculation CBSE, Matriculation CBSE at DAV Public School, NAD, VisakhapatnamBachelor of Technology (B.Tech.) Electrical and Electronics Engineering (Major) & Computer Science and Engineering (Minor), Bachelor of Technology (B.Tech.) Electrical and Electronics Engineering (Major) & Computer Science and Engineering (Minor) at Indian Institute of Technology, GuwahatiMaster of Science - MS Intelligent Information Systems, Master of Science - MS Intelligent Information Systems at Carnegie Mellon UniversityIntermediate Education Mathematics Physics and Chemistry, Intermediate Education Mathematics Physics and Chemistry at Narayana Educational Institutions
English, Telugu, Hindi
Github Skills (14)
named-entity-extraction10
pytorch10
machine-learning10
nlp10
named-entity-recognition10
entities10
sentence-transformers10
python10
natural-language-processing10
bert10
conversational-ai10
entity10
unit-testing9
tf-idf8
Programming languages (2)
Github contributions (5)
cisco/mindmeld
Apr 2021 - Mar 2022
An Open Source Conversational AI Platform for Deep-Domain Voice Interfaces and Chatbots.
Role in this project:
ML Engineer
ML EngineerContributions:201 reviews, 11 commits, 21 PRs in 11 months
Contributions summary:Sai primarily focused on improving the entity resolution component of the MindMeld conversational AI platform. Their contributions included implementing a simple s-bert based entity resolution module, adding a vanilla tfidf ER module, refactoring the ER module, and incorporating a distilled embedder-based entity resolver to accommodate any embedder in the QA module. The user also added methods to extract entity recognizers without building intent classifiers and updated related documentation and unit tests, demonstrating an understanding of the system's architecture.
nlpchatbotsdeep-learningconversationalconversational-ai
murali1996/time_series_classification_prediction
Jun 2018 - Nov 2019
Different deep learning architectures are implemented for time series classification and prediction purposes.
Contributions:47 commits, 4 PRs, 53 pushes in 1 year 5 months
architecturespythonpredictiondeep-learningmachine-learning
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.