03 Record · Adobe
Adobe
- Role
- Computer Scientist II (SDE3)
- Dates
- March 2021 — present
- Location
- Noida, India
- Team
- 15+ engineers
I work on the trust layer of Adobe's document AI: the systems that decide what an assistant is allowed to claim, and prove where each claim came from. That has meant shipping AI Assistant to Acrobat across languages, filing three patents on attribution and summarization, and cutting the cost of running these models in production.
Outcomes
- Shipped AI Assistant in Adobe Acrobat to 10M+ users
- Three patents filed on attribution and document summarization
- Adobe Impact Award
Stack
- Python
- PyTorch
- LLM inference
- AWS
- React
- Node.js
Progression
Jan 2025 — present
Computer Scientist II (SDE3)
- Lead attribution work for document question answering
- Filed two patents in the last eighteen months
Aug 2022 — Dec 2024
Computer Scientist I (SDE2)
- Built AI Assistant features across multiple languages
- Scaled AI Assistant to 10M+ users
Mar 2021 — Jul 2022
Member of Technical Staff II
- Built an ML model optimization framework
- Cut inference time 43.5% and cost 52%