ZipRecruiter

Log In

1

Adversarial Ai Jobs (NOW HIRING)

Finastra

Sr. Adversarial AI Security Engineer

Atlanta, GA · On-site

$110K - $151K/yr

This role will design and deliver realistic adversarial cyberattacks, including the AI enabled/Orchestrated attacks, that will test the effectiveness of the security stack as well as the company ...

HiddenLayer

Lead Engineer, AI Attack Simulation

Portland, OR · On-site +1

$108K - $143K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

HiddenLayer

Lead Engineer, AI Attack Simulation

Austin, TX · On-site +1

$101K - $133K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

HiddenLayer

Lead Engineer, AI Attack Simulation

New York, NY · On-site +1

$112K - $147K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

HiddenLayer

Lead Engineer, AI Attack Simulation

$104K - $138K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

HiddenLayer

Lead Engineer, AI Attack Simulation

$104K - $138K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

HiddenLayer

Lead Engineer, AI Attack Simulation

Seattle, WA · On-site +1

$116K - $153K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

HiddenLayer

Lead Engineer, AI Attack Simulation

Charleston, SC · On-site +1

$95K - $126K/yr

You will lead the architecture and development of systems that translate adversarial AI research and real-world attack techniques into safe, repeatable, and measurable security testing capabilities.

Weekday AI

AI Safety & Red Teaming Specialist

In this role, you will leverage your expertise in adversarial AI, LLM security, and AI safety to identify vulnerabilities, design evaluation methodologies, and improve the resilience of large ...

Blink Health

Senior AI Security Engineer II

New York, NY

$125K - $171K/yr

You will architect and operate a comprehensive AI security program, drive policy and technical controls across the AI lifecycle, lead red-teaming and adversarial testing of AI systems, and serve as ...

next page

Showing results 1-20

All JobsTechnology JobsAdversarial Ai Jobs

Adversarial Ai information

See salary details

$67.5K

$95.2K

$129K

How much do adversarial ai jobs pay per year?

As of Sep 5, 2026, the average yearly pay for adversarial ai in the United States is $95,162.00, according to ZipRecruiter salary data. Most workers in this role earn between $74,000.00 and $116,500.00 per year, depending on experience, location, and employer.

What is adversarial AI?

Adversarial AI refers to techniques and methodologies used to manipulate or deceive artificial intelligence systems, typically by generating inputs that cause the AI to make mistakes. This field also encompasses the study and development of defenses against such attacks to ensure the robustness and security of AI models. Professionals working in adversarial AI research vulnerabilities in machine learning algorithms and work to make AI systems more resilient to malicious manipulation. Adversarial AI is crucial in sectors where AI security and reliability are paramount, such as autonomous vehicles, cybersecurity, and finance.

What are the key skills and qualifications needed to thrive as an adversarial AI specialist?

To thrive as an Adversarial AI Specialist, a strong background in machine learning, deep learning, and computer science—often supported by an advanced degree—is essential. Familiarity with frameworks like TensorFlow and PyTorch, experience in adversarial attack and defense techniques, and knowledge of cybersecurity protocols are typically required. Critical thinking, creativity, and clear communication are valuable soft skills for identifying vulnerabilities and collaborating with cross-functional teams. These capabilities are vital to proactively securing AI systems against evolving threats and ensuring trust in AI-driven applications.

What are some common challenges faced by professionals working in adversarial AI roles?

Professionals in Adversarial AI often grapple with rapidly evolving threats, as new attack vectors and adversarial techniques are constantly emerging. Staying ahead requires continuous learning and experimentation, as well as close collaboration with security, engineering, and research teams to develop robust defenses. Additionally, balancing security with model performance and usability can be complex, requiring thoughtful risk assessments and trade-off decisions. Effective communication of risks and solutions to stakeholders is also a key part of the role.

What is the difference between Adversarial Ai vs Data Scientist?

AspectAdversarial AiData Scientist
Required CredentialsKnowledge of AI, machine learning, cybersecurityDegree in data science, statistics, or related field
Work EnvironmentResearch labs, cybersecurity firms, AI development teamsBusiness, tech companies, research institutions
Industry UsageAI robustness testing, security, model evaluationData analysis, predictive modeling, business insights

Adversarial Ai focuses on creating and defending against malicious inputs to AI models, often within cybersecurity contexts. Data Scientists analyze data to extract insights and build predictive models. While both roles require knowledge of AI and data handling, Adversarial Ai emphasizes security and robustness testing, whereas Data Scientists focus on data analysis and decision-making support.

More about Adversarial Ai jobs

What cities are hiring for Adversarial Ai jobs?

Cities with the most Adversarial Ai job openings:

What states have the most Adversarial Ai jobs?

States with the most job openings for Adversarial Ai jobs include:

What job categories do people searching Adversarial Ai jobs look for?

The top searched job categories for Adversarial Ai jobs are:

Adversarial Ai jobs near you

Sr. Adversarial AI Security Engineer

Finastra

Atlanta, GA • On-site

$110K - $151K/yr

Full-time

Medical, Life, Retirement, PTO

Re-posted 11 days ago

Job description

Who are we?


At Finastra, we're a global leader in financial services software, dedicated to expanding access to financial services and shaping what's next for the industry. Our technology powers missioncritical solutions across Lending, Payments and Universal Banking, supporting over 7,000 customers, including 80% of the world's top 50 banks, in more than 110 countries.

What will you contribute?

This role will design and deliver realistic adversarial cyberattacks, including the AI enabled/Orchestrated attacks, that will test the effectiveness of the security stack as well as the company's ability to detect and respond to these types of attacks.

Key Responsibilities:

  • Lead the planning, design and implementation of assessments and plans, with a focus on AI/ML systems. Continuously test LLM/RAG/agent systems for adversarial risks and automate in CI.

  • Perform full scope adversarial simulation/red team assessments such as design and run adversarial suites (prompt injection, jailbreaks, retrieval poisoning), test model extraction, membership inference, and agent tool-use abuse, deliver PoCs and fixes.

  • Work with the cyber defense Teams to develop new and improved ways to defend the organization

  • Prepare reports containing attack paths, findings/vulnerability information, and mitigation options and recommendations

  • Provide support during ongoing assessments by writing tools and setting up infrastructure

  • Creating automation for specific tasks and operations

  • Research, investigate and evaluate emerging technologies, industry trends and best practices, and vendor solutions to be able to recommend and assess various security products

Required Qualifications:

  • Proven experience with offensive security/research.

  • Demonstrated adversarial AI; Python; replay/fuzzing automation; Security testing standard or Framework such as the MITRE ATLAST Framework

  • Adversarial mindset and critical thinking skills

Preferred Qualifications:

  • Experience in regulated environments.

  • OSCP/GXPN or equivalent a plus.

  • Excellent written and verbal communication skills

  • Experience working in complex, diverse and global (international) environments

We are proud to offer a range of incentives to our employees worldwide. These benefits are available to everyone, regardless of grade, and reflect the values we stand for:

Flexibility: Enjoy unlimited vacation, subject to local regulations and business priorities. Benefit from hybrid working arrangements and inclusive policies such as paid time off for voting, bereavement, and sick leave.

Wellbeing: Access confidential onetoone support through our Employee Assistance Program, connect with our network of Wellbeing Champions and Gather Groups, and take part in monthly events and initiatives designed to help you thrive-inside and outside of work.

Health & Financial Security: Medical, life and disability insurance, retirement plans, lifestyle, and other benefits.*

Sustainability: Paid time off for volunteering and donationmatching opportunities to support causes that matter to you.

Inclusion: Get involved in our inclusion communities, such as Count Me In, Culture@Finastra, Proud@Finastra, Disabilities@Finastra, and Women@Finastra-open to everyone who wants to participate and contribute.

Career Development: Access online learning and accredited courses through our Skills & Career Navigator tool.

Recognition: Take part in our global recognition program, Finastra Celebrates, and share your voice through regular employee surveys that help shape our culture and ways of working.

*Specific benefits may vary by location.

At Finastra, each individual is unique-bringing their own ideas, perspectives, cultural backgrounds, and experiences. We learn from one another, value what makes us different, and create an environment where everyone feels included, supported, and able to be their authentic selves.

Be unique. Be exceptional. Help us make a difference at Finastra.

Applicants for this position need to be located in posted location or their immediate surrounding areas. Due to the requirements of this position, this job posting is not available for, and Finastra will not be considering any applicants who currently reside in New York City or California.

Apply