ZipRecruiter

Log In

1

Adversarial Ai Jobs in Reston, VA (NOW HIRING)

Koniag, Inc.

AI Security Specialist/SME

Washington, DC · On-site

$190K - $212K/yr

Monitor and analyze the AI threat landscape, including emerging adversarial AI attack techniques, AI vulnerability disclosures, and evolving federal AI security guidance, providing timely threat ...

VTG

Staff II/ Staff III AI/ML Engineer

Chantilly, VA

Red teaming and adversarial testing * Bias and fairness assessments * Performance and reliability testing * Human-in-the-loop evaluation strategies Establish and implement AI governance frameworks ...

VTG

Staff II/ Staff III AI/ML Engineer

Chantilly, VA · On-site

Red teaming and adversarial testing * Bias and fairness assessments * Performance and reliability testing * Human-in-the-loop evaluation strategies Establish and implement AI governance frameworks ...

HiddenLayer

Director of Engineering

Washington, DC · On-site +1

We were founded by AI professionals and security specialists with first-hand experience of how insidious adversarial AI attacks can be to detect and defend against. Determined to prove that these ...

New

Jobtailor

AI Director

Reston, VA · On-site

$150 - $200/hr

Monitor and analyze emerging developments in artificial intelligence, adversarial AI, AI regulation, AI security risks to inform community priorities, member discussions, and thought leadership ...

10a Labs

AI Red Teamer, Cyber

Washington, DC · On-site

$100K - $120K/yr

Our adversarial red teaming, model evaluations, and intelligence collection enable engineering, safety, and security teams to stay ahead of evolving threats and deploy AI systems safely. About the ...

10a Labs

AI Red Teamer

Washington, DC · On-site

$70K - $90K/yr

Our adversarial red teaming, model evaluations, and intelligence collection enable engineering, safety, and security teams to stay ahead of evolving threats and deploy AI systems safely. In This Role ...

10a Labs

AI Red Teamer

Washington, DC · On-site

$70K - $90K/yr

Our adversarial red teaming, model evaluations, and intelligence collection enable engineering, safety, and security teams to stay ahead of evolving threats and deploy AI systems safely. In This Role ...

10a Labs

AI Red Teamer, Cyber

Washington, DC · Remote

$100K - $120K/yr

We are seeking an AI Red Teamer with deep cybersecurity expertise to help evaluate the security and ... Develop adversarial testing methodologies to evaluate system security, robustness, and resilience

Wilmerhale

Senior AI Defense Engineer

Washington, DC · On-site

$129K - $177K/yr

The role will translate emerging AI threats into practical defenses, guardrails, policy enforcement layers, monitoring and detections, adversarial test automation, and hardened environments that hold ...

WilmerHale

Senior AI Defense Engineer

Washington, DC · On-site

$129K - $177K/yr

Adversarial Testing & Red Teaming - Identify and utilize adversarial test suites for AI applications (prompt libraries, fuzzing harnesses, automated attack campaigns). Simulate realistic attacker ...

WilmerHale

Senior AI Defense Engineer

Washington, DC

$129K - $177K/yr

Adversarial Testing & Red Teaming - Identify and utilize adversarial test suites for AI applications (prompt libraries, fuzzing harnesses, automated attack campaigns). Simulate realistic attacker ...

previous pagenext page

Showing results 21-40

All JobsAdversarial Ai JobsAdversarial Ai Jobs in Reston, VA

Adversarial Ai information

See Reston, VA salary details

$70.2K

$99K

$134.2K

How much do adversarial ai jobs pay per year?

As of Aug 9, 2026, the average yearly pay for adversarial ai in Reston, VA is $99,002.00, according to ZipRecruiter salary data. Most workers in this role earn between $77,000.00 and $121,200.00 per year, depending on experience, location, and employer.

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.

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 popular job titles related to Adversarial Ai jobs in Reston, VA? For Adversarial Ai jobs in Reston, VA, the most frequently searched job titles are:
What job categories do people searching Adversarial Ai jobs in Reston, VA look for? The top searched job categories for Adversarial Ai jobs in Reston, VA are:
What cities near Reston, VA are hiring for Adversarial Ai jobs? Cities near Reston, VA with the most Adversarial Ai job openings:
Adversarial Ai jobs near you

AI Security Specialist/SME

Koniag, Inc.

Washington, DC • On-site

$190K - $212K/yr

Full-time

Medical, Dental, Vision, Retirement, PTO

Posted 26 days ago

Job description

Koniag Data Solutions, LLC, a Koniag Government Services company, is seeking an AI Security Specialist/SME to support KDS and our government customer in Washington, DC. This position requires the candidate to be able to obtain a Public Trust.
We offer competitive compensation and an extraordinary benefits package including health, dental and vision insurance, 401K with company matching, flexible spending accounts, paid holidays, three weeks paid time off, and more.
Koniag Data Solutions, a Koniag Government Services company, is seeking an experienced AI Security Specialist / Subject Matter Expert (SME) to support the development, implementation, and management of artificial intelligence security programs, policies, and risk management initiatives in support of the U.S. Small Business Administration (SBA). The ideal candidate is a senior-level cybersecurity and AI professional with deep expertise in AI/ML security principles, AI risk management frameworks, and the unique security challenges and considerations associated with the adoption, development, and operation of AI systems within a federal government environment. This individual will serve as SBA's subject matter expert on AI security matters, providing expert guidance and technical leadership to ensure AI systems and initiatives across the SBA are developed, deployed, and operated securely, responsibly, and in compliance with applicable federal AI policies, executive orders, and emerging regulatory requirements.
The AI Security Specialist / SME will serve as the senior technical lead and subject matter expert for AI security at the SBA, working closely with SBA's IT leadership, security teams, data science and AI development teams, program managers, legal counsel, and external partners to develop and implement a comprehensive AI security program that enables SBA to adopt and leverage AI technologies securely, responsibly, and in alignment with federal AI governance requirements.
Principal responsibilities will include but are not limited to:
  • Serve as SBA's senior SME and technical lead for AI security, providing expert guidance, strategic direction, and technical leadership on all matters related to the security of AI systems, machine learning models, and AI-enabled applications across the SBA enterprise.
  • Develop, implement, and maintain SBA's AI security program, including the development of AI security policies, standards, guidelines, and risk management frameworks aligned with applicable federal AI executive orders, OMB AI guidance, NIST AI Risk Management Framework (AI RMF), and other relevant federal AI governance requirements.
  • Lead the conduct of AI security risk assessments and reviews for SBA AI systems and initiatives, evaluating AI-specific security risks including adversarial attacks, model poisoning, data integrity threats, model inversion, and other AI/ML-specific threat vectors, and developing comprehensive risk mitigation strategies.
  • Provide expert security guidance and oversight throughout the AI system lifecycle, from requirements and design through development, testing, deployment, and operations, ensuring AI security requirements are properly integrated at each phase.
  • Develop and maintain AI security assessment methodologies, testing frameworks, and evaluation criteria for assessing the security and trustworthiness of AI systems and machine learning models deployed within the SBA environment.
  • Collaborate with SBA's data science, AI development, and application teams to integrate AI security best practices, secure development guidelines, and security testing requirements into AI development workflows and processes.
  • Lead the development and implementation of AI governance documentation for SBA, including AI use case inventories, AI impact assessments, AI system security plans, and other required AI governance artifacts in alignment with federal AI transparency and accountability requirements.
  • Monitor and analyze the AI threat landscape, including emerging adversarial AI attack techniques, AI vulnerability disclosures, and evolving federal AI security guidance, providing timely threat assessments and recommendations to SBA security leadership.
  • Provide expert guidance on the security implications of generative AI technologies and large language models (LLMs), including the development of SBA policies and guidelines for the secure and responsible use of generative AI tools by SBA personnel and contractors.
  • Collaborate with SBA's privacy team to address the intersection of AI security and privacy, including AI-related privacy risks, data minimization requirements, and the privacy implications of AI model training, deployment, and output
  • Support the integration of AI security considerations into SBA's existing cybersecurity frameworks, risk management processes, and security authorization activities, including the development of AI-specific security control overlays and assessment procedures.
  • Serve as SBA's representative and technical SME in engagements with OMB, CISA, NIST, and other federal partners on AI security-related matters, including participation in interagency AI security working groups and forums.
  • Develop and deliver comprehensive AI security awareness and training programs for SBA personnel and contractors, ensuring all staff understand the security risks, responsibilities, and requirements associated with the use and development of AI systems.
  • Lead and support after-action reviews and lessons learned following AI security incidents or near-misses, translating findings into actionable improvements to SBA's AI security program and practices
  • Develop and deliver AI security briefings, program reports, and strategic recommendations for SBA senior leadership and oversight bodies, providing clear and compelling insights into AI security risks, program status, and compliance posture.
  • Stay at the forefront of AI security research, technology developments, federal policy updates, and industry best practices, applying this knowledge to continuously refine and strengthen SBA's AI security program.

Education and Experience:
Required:
  • Bachelor's degree in Cybersecurity, Computer Science, Artificial Intelligence, Data Science, Information Technology, or a related field from an accredited college or university, OR equivalent combination of education and extensive relevant work experience.
  • 7+ years of progressive experience in cybersecurity, with significant demonstrated experience in AI/ML security, data science security, or a closely related field within a federal government or large enterprise environment.
  • Demonstrated expert-level knowledge of AI/ML security principles, adversarial machine learning concepts, and AI-specific threat vectors including model poisoning, adversarial attacks, model inversion, and data integrity threats
  • Demonstrated familiarity with federal AI governance frameworks and requirements including NIST AI Risk Management Framework (AI RMF), Executive Order 13960, Executive Order 14110, and applicable OMB AI memoranda and guidance.
  • One or more of the following certifications: Certified Information Systems Security Professional (CISSP), Certified Information Security Manager (CISM), or equivalent senior-level cybersecurity certification, supplemented by demonstrated AI/ML security expertise.

Desired:
  • Master's degree or Ph.D. in Cybersecurity, Computer Science, Artificial Intelligence, Data Science, or a related field.
  • Prior experience serving as an AI security SME or advisor supporting a federal civilian agency, preferably the SBA or a similar organization.
  • Certified Artificial Intelligence Security Specialist (CAISS) or equivalent AI security certification, or active pursuit of same.
  • Demonstrated experience with AI red teaming, adversarial robustness testing, or AI penetration testing methodologies.

Required Skills and Competencies:
  • Expert-level knowledge of AI and machine learning concepts, architectures, and development methodologies, with the ability to apply this knowledge to identify, assess, and mitigate security risks across a broad range of AI system types and use cases.
  • Deep expertise in AI/ML security principles and adversarial machine learning, including comprehensive understanding of AI-specific threat vectors such as adversarial examples, model poisoning, backdoor attacks, model inversion, membership inference, and data poisoning attacks.
  • Demonstrated ability to develop and implement comprehensive AI security risk assessment methodologies, testing frameworks, and evaluation criteria for assessing the security and trustworthiness of federal AI systems.
  • Expert-level knowledge of federal AI governance frameworks and requirements including NIST AI RMF, applicable executive orders, and OMB AI guidance, with the ability to translate these requirements into practical AI security program activities and controls.
  • Strong experience collaborating with data science and AI development teams to integrate security best practices and requirements into AI development workflows, MLOps pipelines, and AI system architectures.
  • Solid understanding of the security implications of generative AI technologies and large language models (LLMs), including prompt injection attacks, data leakage risks, model abuse scenarios, and strategies for the secure and responsible deployment of generative AI capabilities.
  • Experience developing AI governance documentation including AI use case inventories, AI impact assessments, and AI system security documentation in alignment with federal AI transparency and accountability requirements.
  • Strong understanding of the intersection of AI security with privacy, data governance, and ethics, including the ability to address AI-related privacy risks and data protection requirements within an AI security program context.
  • Solid understanding of federal cybersecurity frameworks and requirements including NIST SP 800-53, FISMA, and relevant OMB and CISA guidance, and their relationship to AI security program development and implementation.
  • Exceptional written and oral communication skills in English, with the ability to clearly communicate complex AI security concepts, risk assessments, and strategic recommendations to both technical teams and senior non-technical audiences including agency leadership.
  • Strong leadership skills with demonstrated experience providing expert technical guidance and oversight on AI security matters to cross-functional teams including security, IT, data science, legal, and program management staff.
  • Ability to obtain and maintain a Public Trust clearance as required by the SBA.

Desired Skills and Competencies:
  • Prior experience serving as an AI security SME or advisor supporting the SBA or a similar federal civilian agency.
  • In-depth familiarity with SBA's AI initiatives, IT environment, and mission areas, including an understanding of the unique AI security challenges and opportunities associated with SBA's specific use cases and operational context
  • Demonstrated experience with AI red teaming, adversarial robustness testing, or AI penetration testing methodologies, including hands-on experience using adversarial machine learning tools and frameworks such as IBM Adversarial Robustness Toolbox (ART), Microsoft Counterfit, or similar.
  • Advanced knowledge of MLOps practices and platforms and their security implications, including experience integrating AI security controls and testing into ML pipelines and model deployment workflows.
  • Experience with AI supply chain security considerations, including the security risks associated with pre-trained models, open-source AI libraries, and third-party AI services and APIs.
  • Familiarity with AI fairness, explainability, and transparency concepts and their relationship to AI security and trustworthiness in a federal government context.
  • Experience with cloud-based AI/ML platforms and services such as AWS SageMaker, Microsoft Azure Machine Learning, or Google Vertex AI, and their security configurations, access controls, and monitoring capabilities.
  • Knowledge of natural language processing (NLP) and computer vision AI application security considerations and specific threat vectors relevant to these AI domains.
  • Experience participating in federal interagency AI security working groups, NIST AI RMF development activities, or OMB AI governance oversight engagements.
  • Certified Artificial Intelligence Security Specialist (CAISS), AI Security certification from a recognized professional organization, or other relevant advanced AI or cybersecurity certifications
  • Experience developing and delivering AI security training programs for large, diverse federal agency workforces including both technical and non-technical personnel.
  • Familiarity with international AI governance frameworks and standards such as the EU AI Act, ISO/IEC 42001, and their relationship to federal AI security and governance requirements.

Our Equal Employment Opportunity Policy
The company is an equal opportunity employer. The company shall not discriminate against any employee or applicant because of race, color, religion, creed, ethnicity, sex, sexual orientation, gender or gender identity (except where gender is a bona fide occupational qualification), national origin or ancestry, age, disability, citizenship, military/veteran status, marital status, genetic information or any other characteristic protected by applicable federal, state, or local law. We are committed to equal employment opportunity in all decisions related to employment, promotion, wages, benefits, and all other privileges, terms, and conditions of employment.
The company is dedicated to seeking all qualified applicants. If you require an accommodation to navigate or apply for a position on our website, please get in touch with Heaven Wood via e-mail at accommodations@koniag-gs.com or by calling 703-488-9377 to request accommodations.
Koniag Government Services (KGS) is an Alaska Native Owned corporation supporting the values and traditions of our native communities through an agile employee and corporate culture that delivers Enterprise Solutions, Professional Services and Operational Management to Federal Government Agencies. As a who
Koniag logo

About Koniag

Sourced by ZipRecruiter

Industry

Investment management and consulting services

Company size

501 - 1,000 Employees

Headquarters location

Kodiak, AK, US

Year founded

1972

Social media

Facebook

View All Koniag Jobs

Apply