Ege Demir
Machine Learning Engineer at Themis AI- Claim this Profile
Click to upgrade to our gold package
for the full feature experience.
-
Turkish Native or bilingual proficiency
-
English Native or bilingual proficiency
-
German Elementary proficiency
Topline Score
Bio
Credentials
-
NVIDIA DLI Certificate – Fundamentals of Deep Learning
NVIDIAFeb, 2022- Nov, 2024
Experience
-
Themis AI
-
United States
-
Software Development
-
1 - 100 Employee
-
Machine Learning Engineer
-
Sep 2022 - Present
-
-
-
Iowa State University
-
United States
-
Higher Education
-
700 & Above Employee
-
Research Assistant
-
Dec 2021 - May 2022
- Developed a novel adversarial deep learning method using variational autoencoders to reduce training accuracy of CNN-based website fingerprinting attacks.- Trained a CNN model that classifies 15 websites based on website fingerprint in last-level cache with ~90% accuracy to demonstrate method's performance. - Developed a novel adversarial deep learning method using variational autoencoders to reduce training accuracy of CNN-based website fingerprinting attacks.- Trained a CNN model that classifies 15 websites based on website fingerprint in last-level cache with ~90% accuracy to demonstrate method's performance.
-
-
-
Ouva
-
United States
-
Hospitals and Health Care
-
1 - 100 Employee
-
Software Engineer
-
Dec 2019 - Feb 2020
- Trained and evaluated speech-to-text models and cloud platforms for healthcare voice assistant product.- Integrated Google Cloud’s asynchronous speech-to-text APIs into the product’s Python production code-base. - Trained and evaluated speech-to-text models and cloud platforms for healthcare voice assistant product.- Integrated Google Cloud’s asynchronous speech-to-text APIs into the product’s Python production code-base.
-
-
Education
-
-
Iowa State University
Bachelor of Engineering - BE, Computer Engineering
Community
