Avinesh Polisetty
Senior ML Research Scientist at Apple
Milpitas, California, United States
Summary
👤
Senior🎓
Top SchoolAvinesh Polisetty is a Senior ML Research Scientist with 14 years of experience building large-scale NLP and multimodal systems, currently advancing Siri’s multilingual comprehension and on-device intelligence at Apple. He combines deep academic roots—a PhD from TU Darmstadt on human-in-the-loop information preparation—with hands-on production work like deploying a 1.2MB transformer across 41 locales and leading visual QA for open-domain assistants. His background spans industry-impacting projects from Watson Oncology’s clinical NLP to international KG-QA and corpus-driven research, showing fluency across research, engineering, and product contexts. Avinesh excels at scaling models across languages via transfer learning and domain adaptation, and has repeatedly translated novel research (e.g., interactive summarization and live-blog condensing) into deployed features. Known for pragmatically reducing model and pipeline bottlenecks (improving search ranking and lexicon coverage), he bridges clinician and product stakeholders to deliver trusted ML. Based in Milpitas, CA, he uniquely blends multilingual research, medical NLP experience, and on-device model optimization.
14 years of coding experience
12 years of employment as a software developer
Technischen Universität Darmstadt10th class, 10th class at Kendriya Vidyalaya RajahmundryMaster of Science (MS), Computer Software Engineering specialisation in NLP, 8.54/10, Master of Science (MS), Computer Software Engineering specialisation in NLP, 8.54/10 at International Institute of Information Technology
English, Hindi, Telugu
Github Skills (20)
kannada10
multi-document10
bengali10
hindi10
pos-tagger10
urdu10
punjabi10
summarization7
vldb7
interactive3
cosine-similarity3
text-summarization3
multi-task-learning3
similarity2
similarity-search1
Programming languages (4)
Github contributions (5)
UKPLab/acl2017-interactive_summarizer
May 2017 - Nov 2018
A general framework for Interactive Multi-Document Summarization
Contributions:20 commits, 15 pushes, 1 branch in 1 year 6 months
multi-document
avineshpvs/indic_tagger
Nov 2017 - Jan 2021
Indian Language Tagger and Chunker (Hindi, Telugu, Tamil, Marathi, Punjabi, Kanada, Malayalam, Urdu, Bengali)
Contributions:26 commits, 4 PRs, 10 pushes in 3 years 3 months
indian-languagesmarathipos-taggerhindimalayalam
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.