Data Scientist

ReversingLabs was founded in 2009 with the mission of offering organizations the ultimate in threat detection solutions. In 2017, we were honored to receive the JPMorgan Chase Hall of Innovation Award for our truly unique, automated, and scalable static file analysis, malware classification and malware hunting technologies. Our pioneering technologies, exceptional products, and successful customer deployments also drove a $25 million investment in ReversingLabs backed by some of the savviest investors in the world. With our center of development excellence located in Zagreb, and offices in the United States and Switzerland, ReversingLabs is poised to achieve rapid growth and deliver groundbreaking innovation in 2021.

The machine learning team is a part of the static file analysis group in ReversingLabs. The projects include data-driven approaches to file type identification, malware classification, detection of hidden payloads, and extraction of file properties related to security. These projects complement the more conventional static analysis techniques developed by threat analysts and reverse engineers in the group, and aim to be practical for threats present in real-world data distributions. For data, we leverage the existing ReversingLabs file reputation collections and feeds of novel samples received from security industry feeds, threat intelligence, and in-house harvesting. Other than straightforward product-oriented projects, we also engage in more research oriented endeavors aimed at threat hunting, threat intelligence, and data quality in our file metadata collections. The largest challenge of the position is to work with complex data and a shifting data distribution. This often requires an investigative mindset and cooperation with threat analysts and reverse engineers to create finely tuned and reliable solutions.

As a data scientist, you would analyze data to define the scope of individual projects, create datasets, create and test predictive models, and monitor the performance of models on real-world data. The ideal set of skills would be data analysis, cybersecurity domain awareness, general machine learning and modeling, and experience with robust models deployed in production environments, but the position is also an opportunity to develop into these skills. This means that we welcome various backgrounds that could grow into this position, such as machine learning oriented data scientists, data scientists who have worked with predictive models, or cybersecurity practitioners with an interest in data-driven approaches.

Requirements

• Experience working with a GNU/Linux-based OS
• Experience working with Python or similar scripting language(s) for data analysis and visualization
• 2+ years of experience in some field related to this position

Desirable skills

• Experience with predictive models in production environments
• Experience with managing data-driven projects
• Experience with analytics platforms, e.g. Elasticsearch, Kibana
• Experience with machine learning tools, e.g. scikit-learn, Tensorflow, PyTorch
• Experience with Python data science tools, e.g. pandas, matplotlib, scipy, numpy
• Experience with SQL
• Awareness of cybersecurity domain, especially file-based analysis

Benefits

• Flexible working hours
• Competitive compensation and benefits package
• Permanent contract in a fast-growing global company
• Challenging projects in a dynamic, collaborative team
• Great career advancement opportunities - ReversingLabs encourages internal promotion
• Personal improvement through attending leading conferences and seminars in the field