Post Project
Continue with Facebook
Continue with LinkedIn
Invite
ABOUT
מומחה בתחום למידת מכונה עם 8 שנות ניסיון בהובלת פתרונות בינה מלאכותית מרעיון ועד ליישום בסביבות תעשייתיות. מנהיג מוכח עם מומחיות בלמידה עמוקה, ראייה ממוחשבת ומודלי שפה גדולים (LLMs), ותשוקה לבניית יישומי בינה מלאכותית חדשניים המספקים ערך עסקי. מחויב ללמידה עצמית והתקדמות, מחפש תפקיד הנהגה בו אוכל לתרום לפיתוח בינה מלאכותית מתקדמת.
LANGUAGES
Hebrew
Native or bilingual proficiency
English
Full professional proficiency
SKILL DETAILS
Technology
400 ₪
/ hr
AI, Artificial Intelligence
optimized desalination design efficiency by 80% through novel data structuring and multi-class regression algorithms.
Machine Learning
optimized desalination design efficiency by 80% through novel data structuring and multi-class regression algorithms.
Deep Learning
Developed a CNN-based algorithm to optimize numerical simulations, leading to improved performance in a UF filter control cleaning system.
EMPLOYMENT HISTORY
July
2024
-
Today
Senior Machine Learning Researcher
PROMAI- - LLM Development & Optimization: Developed and optimized an Open Source multi-modal LLM for automated work instructions in manufacturing, considering GPU capabilities (precision, quantization), and implementing RAG, prompt engineering, and QLoRA fine-tuning.
- - Mentorship: Provided guidance and mentorship to junior team members.
- - Computer Vision: Involved in real-time image segmentation and detection project using CNOS and DINO.
November
2023
-
Today
Research Scientist
Tel Aviv University- The Center for AI and Data Science (TAD)
- - Developed a multimodal deep learning model for geospatial analysis: Combined satellite imagery and tabular data to forecast flood impact on water quality using developed algorithms with Google Products such as Google Earth API.
February
2022
-
February
2024
Applied Machine Learning Engineer
NI (Now Emerson)- - Led wafer classification project: Developed, deployed, and scaled an explainable model using SHAP for wafer classification. Built CI/CD pipelines for automation and integrated user feedback for continuous improvement. Deployed on AWS SageMaker.
- - Time series analysis expertise: Applied advanced forecasting techniques to predict EV battery performance.
January
2019
-
February
2022
Data Scientist
IDE Technologies LTD- - Spearheaded machine learning R&D initiatives, including a project that optimized desalination design efficiency by 80% through novel data structuring and multi-class regression algorithms.
COURSES & CERTIFICATIONS
2024
Generative AI with Large Language Models
deeplearning.ai
2020
Deep Learning Specialization
deeplearning.ai
2020
SQL for Data Science
University of California, Davis
2019
Machine Learning
Stanford University
EDUCATION
2018
-
2021
M.Sc. Mechanical Engineering
Tel Aviv University- - Final Project: Developed a CNN-based algorithm to optimize numerical simulations, leading to improved performance in a UF filter control cleaning system.
- - Project on using ResNet for predicting tau-tau decay events at CERN in TensorFlow.
- - Forecasting significant height of sea waves using time series models.
2014
-
2018
B.Sc. Mechanical Engineering
Tel Aviv University- - Research assistant utilizing Python OpenCV for video tracking moth's movements.
ARMED FORCES
2008
-
2014
סרן
חיל תקשוב
PATENTS & INVENTIONS
May
2024
SYSTEM AND METHOD FOR AUTOMATIC WAFER MAP CLASSIFICATION
20240170348- A method of testing semiconductor wafers includes receiving a wafer bin map for a semiconductor wafer, wherein the wafer bin map includes a plurality of points corresponding to a plurality of defective dies fabricated on the semiconductor wafer, identifying a cluster of points in the wafer bin map from the plurality of points, and generating a filtered bin map using the cluster of points. The method also includes extracting a set of features for the filtered bin map, wherein the set of features comprises a set of global features common to the semiconductor wafer and a set of cluster features specific to the filtered bin map, executing a trained machine learning model using the set of features as inputs to generate a pattern classification, and determining, based on the pattern classification, that the semiconductor wafer includes a pattern of defective dies caused by a defective manufacturing process.
