Pezhman Sheini

ArcSight, Micro Focus/OpenText Apr 2022– May 2023Data Scientist for Cybersecurity Research 40 Hours/Week

Submitted a patent (pending) for automating the preprocessing of complex logs
Developed a comprehensive data preparation process, including log parsing, ETL, and feature extraction and selection techniques
Successfully implemented and deployed machine learning and deep learning solutions for log analysis and anomaly detection tools, significantly improving the decision-making process of ArcSight's support team. Implementation of these tools has resulted in a significant reduction in investigation time, and enhanced operational efficiency by an order of magnitude
Prepared presentation materials and formal business case documents for senior management, effectively promoted findings and driving science-based decision support recommendations derived from the successful implementation and deployment of machine learning and deep learning solutions for log analysis and anomaly detection tools
Characterized hostnames and built a model to compute a risk score for each hostname. When utilizing this score to predict malicious hostnames, we achieved a 30% reduction in false positives and improved the overall accuracy greater than 27% compared to the legacy approach
Skills: Exploratory Data Analysis, Anomaly detection, LLM, Transformer, Generative AI (OpenAI), Pattern detection, Event prediction, MLFlow, AI/ML development lifecycle, Vertica, Statistical modeling, Documentation

The University of Colorado – Boulder, CO 80309 Sep 2020 – Apr 2022Postdoctoral Research Associate / Data Scientist 40 Hours/Week

Led the research and development efforts for pathogen surveillance software on persistent memory (Optane) in collaboration with Intel Corp and Columbia University
Conducted a comprehensive analysis of traditional techniques for pathogen surveillance and identified trends to optimize strategies
Developed a groundbreaking approach for DNA representation using image representation of DNA sequences, Self-supervised Learning (SSL), and information retrieval trajectories
Implemented a novel k-mismatch similarity search by designing and implementing a hamming weight tree data structure
Skills: Data Structures, Big Data, AWS, Computer vision, Self-Supervised Learning, Variational Autoencoder, ETL, Debugging, CI/CD, TensorFlow, MLOps, Spark, Classification, Information Retrieval, Data Visualization

The University of Alabama – Tuscaloosa, AL 35487 Aug 2016 – Aug 2020Graduate Research Assistant / Data Scientist 20 Hours/Week

Designed and developed a novel approach to generate multilingual word embeddings using universal concepts and graph theories – PhD Dissertation
Designed and developed sentiment analysis, information retrieval, and text classification applications that utilize multilingual word embeddings
Contributed training resources (including quality assurance guidelines) for undergraduates and assisted the PI with data analysis and publications
Skills: Artificial Intelligence, Natural Language Processing (NLP), Social media data analysis, User modeling, XLNET, TensorFlow, Sentiment Analysis, Information Retrieval, Social Media Event Detection, Quantitative Modeling, BERT, Web Scrappers, ML Algorithms, Predictive Analysis, Language Modeling, Transfer Learning

The University of Alabama (UA) – Tuscaloosa, AL 35487 Aug 2016 – May 2019Graduate Teaching Assistant 20 Hours/Week

RM - Pro Innovation – Louisville, KY 40299 May 2015 – Aug 2015Cyber Security Analyzer and Data Manager 40 Hours/Week

Designed, implemented, and consulted the company employees about “Disaster Recovery Procedures and Protocols” for “The Data Center”
Performed full spectrum CNO.

Assessed cyber security vulnerabilities (CNA & CNE) and implemented a mitigation solution (CND) tailored for the company’s goals and objectives
Provided technology planning, design, and administration for “The Data Center” and its network infrastructure
Supported more than 40 remote web servers
Identified the requirements and implemented the most efficient and cost-effective solutions for the resilient network system

Western Kentucky University – Bowling Green, KY 42101 Jan 2015 – May 2016Graduate Research Assistant20 Hours/Week

Implemented research objectives, provided research support, and mentored undergraduates
Skills: Cloud Architecture, OpenStack, Hypervisors, Linux, Bash, Cyber Security, Network/Cloud Security, Cyber-attacks, DDoS Attacks

The University of Alabama, College of Engineering - Tuscaloosa, AL 35487 Aug 2016 – Aug 2020Ph.D. of Computer Science GPA: 3.9/4.0

Dissertation titled “Multilingual Word Embeddings with Universal Concepts and their Applications.”
Other related research: Cyber Security (e.g., DDoS attacks Mitigations)
Courses: Robotics, Software Development and Testing, Web Applications and Databases, Algorithms and Data Structures, Compilers and Operating Systems, Adv.

Computer

Communication & Networks, Computer Security, Cryptography & Data Security

Western Kentucky University – Bowling Green, KY 42101 Sep 2014 - Aug 2016

Master of Science GPA: 3.6/4.0

Thesis titled “Performance Impact of DDoS Attacks on Three Virtual Machine Hypervisors”
Other related research: Cloud Security and Attack Strategies

Islamic Azad University – Tehran, Iran Sep 2004 - Aug 2009

Major: Computer Engineering Hardware
Capstone Project: Implementing follow liner robots
Courses: Introduction to Software Engineering, Computer Organization, Applied Algorithms for Engineering, Microprocessors, Probability Theory, Systems Programming, Control Systems, Microcomputer Architecture

About