Full-stack Data Scientist
2020 - 2022Freelance clients- Scraped data from many different sources and set up robust pipelines for regular data processing in AWS.
- Built a system for providing regular reports based on various data sources; it is an entirely automatic cloud-based system.
- Created internal websites for data monitoring and control.
Technologies: Big Data, JavaScript, React, Scraping, AWS, APIs, Python, PandasData Engineer and Data Scientist
2019 - 2020Barclays- Created an anomaly detection model that ran in Spark and provided anomalies for a transaction audit and visualization tool.
- Worked on a data transfer project that spanned multiple departments and platforms and helped to safely transfer data within the company.
- Designed and developed solutions for big data platforms.
Technologies: Scikit-learn, Python, Scala, SparkData Scientist
2013 - 2019Cisco Systems- Created classifiers and anomaly detectors for catching malware in network traffic using metadata.
- Performed data extraction and analysis, designed features, and built classification models using various machine learning techniques.
- Worked with big data technologies on a daily basis, creating and optimizing a lot of complex analysis jobs in Spark that ran on large volumes of data.
- Had to keep up with trends in machine learning and data science and implemented many state-of-the-art methods from scientific publications.
- Drafted several US patterns on network security and machine learning. Many patents were successfully submitted, some already granted by the US Patent Authority.
- Published commercial blogs and contributed to scientific papers.
Technologies: Amazon Web Services (AWS), AWS, Scalding, Scala, Spark, Scikit-learn, Python, MATLABDeveloper
2012 - 2013Cognitive Security- Ran malware in sandboxed environments and gathered network telemetry.
- Analyzed network telemetry from malware.
- Designed detection algorithms for the malware based on the analysis.
Technologies: Wireshark, Java
Ivan Nikolaev
Data Visualization Developer in Prague, Czech Republic
Member since November 21, 2019
Ivan has experience working as a data scientist and a data engineer in network security and finance industries. This includes processing and cleaning data, formalizing business problems and creating solutions by designing features and applying machine learning techniques to solve the problems. He works with big data using Spark and MapReduce, and can visualize and present results to stakeholders in an easy-to-understand format.
Ivan is now available for hire
Portfolio
- Freelance clientsBig Data, JavaScript, React, Scraping, AWS, APIs, Python, Pandas
- BarclaysScikit-learn, Python, Scala, Spark
- Cisco SystemsAmazon Web Services (AWS), AWS, Scalding, Scala, Spark, Scikit-learn, Python...
Experience
- Data Visualization 7 years
- Data Science 7 years
- Big Data 6 years
- AWS 5 years
- Python 4 years
- Scraping 4 years
- Pandas 4 years
- React 2 years
Availability
Full-time
Preferred Environment
IntelliJ, Git, Spark, Scala, Python, Linux, MacOS
The most amazing...
...project I've worked on is a classifier that detected network endpoints infected by malware that performed cryptomining.
Employment
Experience
- Distributed Manipulation by Shaping Magnetic Field (MagMan platform)http://aa4cc.dce.fel.cvut.cz/content/distributed-manipulation-shaping-magnetic-field-magman-platform
I participated in this project by measuring the responses of a metal ball to forces created by a magnetic coil. I used these measurements to create a model that was able to activate the coils to provide the required force on the object in real time. The model was based on numerical solver CPLEX by IBM.
This was implemented in Simulink and allowed real-time manipulation of the metal ball using a field of magnetic coil actuators.
A video was created based on this project that won Matlab and Simulink Student Design Challenge 2013.
https://youtu.be/AhS_2gU1qW0
Skills
Languages
Python, JavaScript, HTML, Java, Scala, SQL, CSS, Julia, BashOther
Algorithms, Big Data, Data Scraping, Scraping, Data Visualization, Data Analysis, AWS, Machine Learning, Web Scraping, Front-end, Full-stack Development, GPT-3, Cython, APIsFrameworks
Spark, Scrapy, Flask, SeleniumLibraries/APIs
REST APIs, Scalding, Matplotlib, Scikit-learn, NumPy, PyTorch, React, PandasTools
MATLAB, Git, Jupyter, IntelliJ, Wireshark, YourKitParadigms
Data Science, ETLPlatforms
Linux, Jupyter Notebook, Docker, MacOS, Amazon Web Services (AWS)Storage
PostgreSQL, MySQL, MongoDB
Education
- Master's Degree in Cybernetics and Robotics, Systems and Control Specialization2012 - 2014Czech Technical University - Prague, Czech Republic
- Bachelor's Degree in Cybernetics and Robotics, Systems and Control Specialization2009 - 2012Czech Technical University - Prague, Czech Republic
