Heading
Princeton, NJ
Internship
Onsite
$32/hr - $36/hr
Intern
Siemens empowers customers to transform the industries that form the backbone of economies. They are seeking a highly motivated software development intern to contribute to a project leveraging Artificial Intelligence to detect weaknesses in source code, focusing on data curation and augmentation for vulnerability detection.
Apply NowResponsibilities
- Collect and curate data from publicly available vulnerability databases to build high-quality datasets.
- Clean and preprocess data to ensure it meets quality standards, addressing inconsistencies and improving data usability for AI training.
- Define and implement strategies for data augmentation, enhancing datasets with diverse and representative examples for each Common Weakness Enumeration (CWE).
- Collaborate with cybersecurity experts, data scientists and developers to integrate datasets into AI models, enabling accurate identification of source code weaknesses.
- Contribute to the development of requirements by proposing data enhancement and augmentation strategies through research and brainstorming sessions.
- Maintain clear documentation of data sources, cleaning processes, and augmentation strategies to ensure reproducibility and transparency.
- Participate in development cycles, including meetings, iterative development, and design sessions, ensuring alignment with project goals and timelines.
- Work collaboratively with other team members, document learnings and project progress, and regularly present results to the research and consulting team.
Qualification
Required
- B.S. in cybersecurity, computer science, data science, or another degree from an accredited university with a strong cybersecurity focus.
- Familiarity with Common Weakness Enumerations (CWEs) and understanding of their role in software security assessments.
- Proficiency in data cleaning, preprocessing, and augmentation techniques, with experience in Python or a similar programming language.
- Capability and interest in quick prototyping and experimentation to explore data augmentation strategies.
- Hands-on experience in Linux environments, including command-line usage and shell scripting.
- Experience with professional software development tools and workflows, such as Git, Jira, or GitLab.
- Excellent written and verbal proficiency in English
Preferred
- Pursuing a M.Sc. in cybersecurity, computer science, or data science.
- Experience with vulnerability databases, software security, or AI applications in cybersecurity
- Knowledge of data collection tools and APIs, with experience in web scraping and data pipeline creation being a strong plus.
- Interest in control systems
- Effective communication and teamwork skills, essential for collaborating with other interns and project stakeholders.
- Eagerness to learn and adapt, with a willingness to delve into new tools and technologies as required by the project.
Benefits
- Relocation and housing allowances
- A variety of health and wellness benefits