- Location
- Zagreb, Grad Zagreb, Croatia · published
- Type
- Full-time
- Department
- Education
- Seniority
- Senior
- Source
- Workable
Description
At ReversingLabs, we are providing the world’s largest threat intelligence repository to protect software development and power advanced security solutions, keeping the leading cybersecurity organizations and Fortune 500 enterprises informed and ahead of the threats. Only ReversingLabs delivers the software package analysis speed and depth needed to protect against this critical area of risk.
Our vision is clear. Arming every company with end-to-end insights to ensure development releases securely, IT purchases safely, and the SOC can effectively detect, isolate and respond. We are seeking extraordinary talent for this game changing opportunity to help forge this transformational journey at ReversingLabs.
ReversingLabs owns the largest file reputation database with records for over 70 billion samples. Our systems add millions of records daily, using in-house classification algorithms which decide whether a file, URL or domain is malicious or safe to use. We are looking for an experienced Data Quality Engineer to join the team that builds these algorithms. The role combines data analysis, malware classification and software development, with data at its core.
As part of the team you’ll evaluate classification components, set up dashboards and monitoring to measure performance, identify gaps and propose improvements. To be successful in this role you will need experience in data analysis, data science or a similar role working with large datasets, and an understanding of popular data analysis tools and databases. We're a small, focused team where everyone's contribution is visible, and your work will directly shape the accuracy of our products and the trust customers place in them.
Responsibilities
- Research and evaluate new and existing detection technologies, and recommend improvements that increase classification accuracy and coverage
- Collect, process and analyze large volumes of structured, semi-structured and unstructured data from different sources, and turn it into reliable insights and decisions
- Build dashboards, monitoring and alerting that track classification quality and engine performance, catch issues early, and support decisions with comparisons to other vendors and company-wide statistics
- Write and maintain efficient, clean, production-ready Python code, including libraries, APIs and services
- Own projects end to end and be the point of contact for teams integrating our algorithms