Cyber Security

Description: About the Role

We are seeking a motivated Cybersecurity Data Science Contractor with a strong foundation in data science, machine learning, and a demonstrated interest in cybersecurity. This role bridges the gap between advanced data-driven techniques and practical security operations. You will work alongside experienced cybersecurity professionals to analyze security telemetry, develop models for threat detection, and apply modern data science methods to real-world security problems.

Responsibilities

• Support the development of data-driven models to improve detection of threats, anomalies, and insider risks.
• Apply machine learning techniques such as gradient descent, logistic regression, clustering, and neural networks to cybersecurity use cases.
• Perform exploratory data analysis (EDA) on diverse security datasets (endpoint, network, cloud, identity, vulnerability).
• Collaborate with the security operations and threat intelligence teams to design metrics, features, and models that enhance detection and response.
• Contribute to automation workflows, anomaly scoring models, and visualization dashboards for SOC analysts.
• Research and experiment with AI/ML techniques (e.g., embeddings, NLP, anomaly detection) to extract actionable insights from large volumes of security data.
• Present findings and proof-of-concept results to both technical and non-technical stakeholders.

Required Qualifications

• 2-3 years of experience
• Currently pursuing a degree (Bachelors, Master’s, or PhD) in Data Science, Computer Science, Cybersecurity, Applied Math, or related field.
• Strong understanding of machine learning fundamentals (gradient descent, optimization, supervised/unsupervised learning).
• Experience with Python and data science libraries (NumPy, Pandas, scikit-learn, PyTorch or TensorFlow).
• Basic knowledge of cybersecurity concepts such as threats, vulnerabilities, intrusion detection, and MITRE Telecommunication&CK.
• Ability to analyze large datasets and communicate findings clearly.