Staff Research Scientist- Visa Research

Visa is a world leader in payments and technology, with over 259 billion payments transactions flowing safely between consumers, merchants, financial institutions, and government entities in more than 200 countries and territories each year. Our mission is to connect the world through the most innovative, convenient, reliable, and secure payments network, enabling individuals, businesses, and economies to thrive while driven by a common purpose - to uplift everyone, everywhere by being the best way to pay and be paid.

Make an impact with a purpose-driven industry leader. Join us today and experience Life at Visa.

Visa Research: Visa Research is an organization that focuses exclusively on the scientific foundations of existing,emergingand future commerce-related technologies. With the establishment of a formal research organization and the associated long-term commitment to technology research, Visa joins the ranks of a small number of industry leaders with both the insight and ability tosubstantially influenceand systemicallyimpactthe future.

Our Generative AI Trust & Efficiency (GATE) research team is at the forefront of building safe, reliable, and secure artificial intelligence. We are a collaborative group of researchers dedicated to solving the most challenging problems in AI safety and security. Our mission is to ensure that as generative AI models and agents become more capable, they are also developed and deployed responsibly. We foster a culture of innovation, encouraging our team to publish their work in top-tier conferences and collaborate with the broader research community.

Role Overview:

We are seeking a Staff Research Scientist to join our research efforts in the security and safety of Generative AI. In this role, you will be instrumental in shaping the future of trustworthy AI. You will conduct cutting-edge research on the vulnerabilities of LLMs and AI agents and develop novel defense mechanisms. Your work will directly influence the security and reliability of our products, protecting our users and systems from adversarial attacks. This is a unique opportunity to make a significant impact on the responsible development of AI.

Responsibilities:

• Conduct innovative research on attack and mitigation methods for LLMs and AI agents, including but not limited to jailbreaking, prompt injection, and other red teaming techniques.
• Design and lead technical security research in the field of LLMs to identify and address AI-specific security threats.
• Develop novel methodologies and frameworks to evaluate and enhance the reliability and safety of AI agents.
• Investigate and develop privacy-preserving technologies to safeguard data within LLM and AI agent ecosystems.
• Collaborate closely with engineering and product teams to translate research findings into practical, production-level solutions.
• Author and publish research papers in top-tier AI and security conferences (e.g., NeurIPS, ICML, ICLR, CCS, S&P, NDSS, USENIX Security).

This is a hybrid position. Expectation of days in office will be confirmed by your hiring manager.

Basic Qualifications:

• Ph.D in Computer Science, Computer Engineering, Electrical Engineering, CIS/MIS, Data Science, Cybersecurity or a related field.

Preferred Qualifications:

• Demonstrated experience in AI security research, including areas such as adversarial machine learning, model robustness, or privacy AI.
• Strong programming skills in Python and deep learning frameworks such as PyTorch.
• A track record of publications in top-tier academic conferences related to AI, machine learning, or security.
• Proven experience in red teaming AI models, with hands-on experience in jailbreaking, prompt injection, and other adversarial attack methods.
• Some understanding of the architecture and inner workings of LLMs and other generative models.
• Experience in developing and deploying security solutions for large-scale AI systems.
• Nice to have-Familiarity with privacy-enhancing technologies such as differential privacy, federated learning, or homomorphic encryption.

Work Hours: Varies upon the needs of the department.

Travel Requirements: This position requires travel5-10% of the time.

Mental/Physical Requirements: This position will be performed in an office setting. The position will require the incumbent to sit and stand at a desk, communicate in person and by telephone, frequently operate standard office equipment, such as telephones and computers.

Visa is an EEO Employer. Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability or protected veteran status. Visa will also consider for employment qualified applicants with criminal histories in a manner consistent with EEOC guidelines and applicable local law.

Visa will consider for employment qualified applicants with criminal histories in a manner consistent with applicable local law, including the requirements of Article 49 of the San Francisco Police Code.

U.S. APPLICANTS ONLY: The estimated salary range for a new hire into this position is $152,200.00 to $220,850.00 USD per year, which may include potential sales incentive payments (if applicable). Salary may vary depending on job-related factors which may include knowledge, skills, experience, and location. In addition, this position may be eligible for bonus and equity. Visa has a comprehensive benefits package for which this position may be eligible that includes Medical, Dental, Vision, 401 (k), FSA/HSA, Life Insurance, Paid Time Off, and Wellness Program.