You will be responsible for the AI models that power our CAASM (Cyber Asset Attack Surface Management) capabilities and our advanced Vulnerability Prioritization and Remediation engines.
We are building the intelligence layer that helps organizations implement a Continuous Threat Exposure Management (CTEM) framework. You will build models that normalize fragmented data from hundreds of sources, calculate complex risk scores, and prioritize which exposures actually pose a threat to the business.
We are looking for an experienced and creative data scientist, with a software development touch, to join our Data Science and our family. A data scientist that understands and loves data, and lots of it.
What you will do…
Solve Applied Product Challenges: Deep-dive into our product ecosystem to identify and solve high-impact problems. You will translate complex customer needs into scalable ML features that directly improve the user experience.
Lead Exposure Intelligence R&D: Develop features that unify asset data (CAASM) with threat intelligence. This includes building models for entity resolution (deduplicating assets across fragmented sources) and automated risk assessment.
Advanced NLP & Knowledge Extraction: Use NLP and LLMs to parse unstructured security data-such as CVEs, threat intel feeds, and security advisories-to automate the mapping of vulnerabilities to specific business contexts.
Predictive Prioritization: Design and optimize algorithms that go beyond static CVSS scores. You will incorporate exploitability (EPSS), reachability, and business criticality to help clients focus on the 1% of exposures that matter most.
End-to-End Ownership: Work closely with Product Managers and Data analysts and Engineers to ensure your models aren't just accurate in a notebook, but are robust, explainable, and deliver clear value within the product UI.
Graph-Based Attack Surface Mapping: Identify hidden patterns and relationships between assets, users, and vulnerabilities to visualize the potential "blast radius" of a security gap.
Academic Background: M.Sc./PhD in Computer Science, Statistics, Engineering, or a related field (or equivalent high-level professional experience).
Industry Experience: 6+ years in Data Science, with a heavy focus on NLP and solving complex, real-world problems using ML/Deep Learning.
Technical Mastery: Hands-on experience with PyTorch, Hugging Face, scikit-learn, and SQL. Familiarity with processing large-scale datasets (PySpark, or similar) is highly valued.
Domain Awareness: Proven ability to apply statistical modeling to cybersecurity, risk management, or complex system analysis. Experience with Vulnerability Management or Graph Theory is a significant plus.
Product and collaborative Driven Mindset: You are obsessed with understanding the "Why" behind the data. You enjoy learning the nuances of the product and the cybersecurity domain to ensure your DS solutions are highly applicable.
