Specialized training or certifications in generative artificial intelligence red teaming, adversarial machine learning, artificial intelligence security, cybersecurity, responsible artificial ...
Specialized training or certifications in generative artificial intelligence red teaming, adversarial machine learning, artificial intelligence security, cybersecurity, responsible artificial ...
AI Cybersecurity Engineer
Oaks, PA · On-site
Deep expertise in AI/ML security principles including adversarial machine learning, model security, data poisoning detection, and prompt injection defense. * Expert-level knowledge of AI/ML ...
AI Cybersecurity Engineer
Oaks, PA · On-site
Deep expertise in AI/ML security principles including adversarial machine learning, model security, data poisoning detection, and prompt injection defense. * Expert-level knowledge of AI/ML ...
AI Engineer
Philadelphia, PA · On-site
$50K - $112K/yr
Certifications aligned to data engineering, machine learning, and cloud platforms, including AWS ... and adversarial benchmarking, to assess reasoning, tool-calling reliability, and output ...
AI Engineer
Philadelphia, PA · On-site
$50K - $112K/yr
Certifications aligned to data engineering, machine learning, and cloud platforms, including AWS ... and adversarial benchmarking, to assess reasoning, tool-calling reliability, and output ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or relevant fields * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
Principal AI/ML Engineer (Large Language Model) (TS/SCI) {S} with Security Clearance
King Of Prussia, PA · On-site
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
Principal AI/ML Engineer (Large Language Model) (TS/SCI) {S} with Security Clearance
King Of Prussia, PA · On-site
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
MS or PhD in machine learning, computer science, mathematics, or related fields. * Experience ... Generative Adversarial Networks and Variational Autoencoders * Reinforcement learning and ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Secure the full AI and machine learning lifecycle, including data ingestion, model development ... Integrate automated security validation, adversarial testing, and model robustness assessments into ...
Leads the design and implementation of security strategies for AI and machine learning ecosystems, including threat detection, model security, adversarial attack mitigation, and risk management.
Leads the design and implementation of security strategies for AI and machine learning ecosystems, including threat detection, model security, adversarial attack mitigation, and risk management.
Research Engineer - Post-Training & Small Language Models (SLMs), Healthcare AI
Philadelphia, PA · On-site
... Machine Learning, Artificial Intelligence, Applied Mathematics, Computational Linguistics, or a ... Perform red teaming and adversarial testing to identify alignment failures, unsafe behaviors ...
Research Engineer - Post-Training & Small Language Models (SLMs), Healthcare AI
Philadelphia, PA · On-site
... Machine Learning, Artificial Intelligence, Applied Mathematics, Computational Linguistics, or a ... Perform red teaming and adversarial testing to identify alignment failures, unsafe behaviors ...
Adversarial Machine Learning information
See Philadelphia, PA salary details
$15.04 - $16.05
4% of jobs
$16.05 - $17.07
3% of jobs
$17.07 - $18.08
10% of jobs
$18.72 is the 25th percentile. Wages below this are outliers.
$18.08 - $19.10
13% of jobs
$19.10 - $20.11
13% of jobs
The median wage is $20.70 / hr.
$20.11 - $21.13
13% of jobs
$21.13 - $22.14
11% of jobs
$22.92 is the 75th percentile. Wages above this are outliers.
$22.14 - $23.15
12% of jobs
$23.15 - $24.17
14% of jobs
$24.17 - $25.18
6% of jobs
$25.18 - $26.20
2% of jobs
$15
$21
$26
How much do adversarial machine learning jobs pay per hour?
As of Aug 7, 2026, the average hourly pay for adversarial machine learning in Philadelphia, PA is $21.52, according to ZipRecruiter salary data. Most workers in this role earn between $18.94 and $23.03 per hour, depending on experience, location, and employer.
What are some common challenges faced by professionals working in adversarial machine learning roles?
Adversarial Machine Learning professionals often face the challenge of staying ahead of rapidly evolving attack techniques that can compromise model integrity and security. Managing the balance between model performance and robustness is another key difficulty, as defenses against adversarial attacks can sometimes reduce accuracy or increase computational costs. Collaboration with data scientists, security teams, and software engineers is vital for developing resilient models and implementing effective defenses. Staying current with the latest research and tools is essential for success in this dynamic field.
What are the key skills and qualifications needed to thrive as an adversarial machine learning specialist, and why are they important?
To excel in Adversarial Machine Learning, you need a strong background in machine learning, deep learning, statistics, and computer science, typically supported by an advanced degree in a related field. Familiarity with frameworks like TensorFlow or PyTorch, experience with adversarial attack and defense libraries, and knowledge of security protocols are crucial. Creative problem-solving, critical thinking, and strong communication skills help in designing robust models and explaining complex threats to stakeholders. These competencies are vital to anticipate vulnerabilities, safeguard AI systems, and ensure the reliability of machine learning models in real-world applications.
What is the difference between Adversarial Machine Learning vs Data Scientist?
| Aspect | Adversarial Machine Learning | Data Scientist |
|---|---|---|
| Credentials | Knowledge of machine learning, cybersecurity, and threat detection | Degree in data science, statistics, or related fields |
| Work Environment | Research labs, cybersecurity teams, AI development | Business analytics, data analysis, model development |
| Industry Usage | AI security, cybersecurity, machine learning research | Business, finance, healthcare, tech companies |
Adversarial Machine Learning focuses on understanding and defending AI models against malicious inputs, often within cybersecurity contexts. Data Scientists analyze data to extract insights, build models, and support decision-making across various industries. While both roles require machine learning knowledge, Adversarial Machine Learning emphasizes security and robustness, whereas Data Scientists focus on data analysis and predictive modeling.
What is adversarial machine learning?
Adversarial machine learning is a field of study focused on understanding and defending against attacks that manipulate machine learning models by feeding them deceptive input, known as adversarial examples. These attacks can cause models to make incorrect predictions, raising concerns about the security and reliability of AI systems, especially in critical applications like image recognition and autonomous vehicles. Researchers in this area develop techniques to detect, prevent, and mitigate these vulnerabilities to make machine learning systems more robust.
What are popular job titles related to Adversarial Machine Learning jobs in Philadelphia, PA? For Adversarial Machine Learning jobs in Philadelphia, PA, the most frequently searched job titles are:
What job categories do people searching Adversarial Machine Learning jobs in Philadelphia, PA look for? The top searched job categories for Adversarial Machine Learning jobs in Philadelphia, PA are:
What cities near Philadelphia, PA are hiring for Adversarial Machine Learning jobs? Cities near Philadelphia, PA with the most Adversarial Machine Learning job openings:
Other
Posted 16 days ago
Deloitte rating
8.2
Based on 92 frontline employees who took The Breakroom Quiz
45th of 150 rated financial services
Job description
Cyber Digital Trust and Online Safety Manager
The Digital Trust & Online Protection Professional will advise clients in developing, managing, and implementing policies, procedures, and strategies to ensure a safe, compliant, and trustworthy environment for our users. This individual will scale and mature digital trust and safety processes, including content compliance, user protection, and regulatory adherence across our platforms for our clients. Working closely with cross-functional stakeholders, this role will monitor regulatory changes, manage risks, and enhance our organization's approach to content safety, user trust, and online integrity.
Recruiting for this role ends on 12/31/3026.
Work you'll do
As a Manager, Strategy, Growth, and Transformation on the Deloitte Cyber team, you will be responsible for:
- Designing and executing testing scenarios to identify how prompts or user inputs could be manipulated to generate harmful, misleading, or misaligned generative artificial intelligence outputs.
- Researching emerging prompt injection, jailbreak, and adversarial testing techniques to evaluate model weaknesses, bias, factual inaccuracy, and misalignment with user intent.
- Assessing the effectiveness of content moderation systems in detecting unsafe outputs and documenting vulnerabilities, failure patterns, and potential misuse impacts.
- Recommending improvements to moderation policies, flagging mechanisms, training data, and governance controls based on testing findings.
- Collaborating with generative artificial intelligence development, content moderation, and cross-functional stakeholders to strengthen security, trust, safety, and responsible use outcomes.
- Developing multimodal test content and novel prompt manipulation methods to identify failure modes across text and other model inputs.
A successful candidate would possess these skills:
- Ability to work independently and collaborate as part of a team
- Effective written and verbal communication skills
- Meticulous attention to detail and quality of work product
- Ability to build and sustain professional relationships
- Ability to lead projects or workstreams
- Ability to manage and prioritize multiple tasks in a fast-paced and dynamic environment
- Strong interpersonal skills and professional demeanor
- Ability to meet deadlines
- Ability to mentor and provide clear guidance to others
The team
Enables trust and safety of online communications and digital products, protecting users, consumers, and patients from harm. Enables clients to provide consumer confidence in knowing with whom they are dealing and ensuring the integrity of access to data.
Qualifications
Required:
- Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Cybersecurity, Linguistics, Psychology, or a related field, or equivalent professional experience
- 10+ years of experience in threat modeling and simulation, prompt generation and analysis, novel testing, and reporting and improvement
- Demonstrated hands-on experience, portfolio work, publications, or research in prompt injection, jailbreak testing, model evaluation, adversarial machine learning, multimodal artificial intelligence safety, or generative artificial intelligence vulnerability assessment
- Ability to travel 25-50%, on average, based on the work you do and the clients and industries/sectors you serve.
- Limited immigration sponsorship may be available.
Preferred:
- Doctor of Philosophy (PhD) in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Cybersecurity, Linguistics, Psychology, or a related field, or equivalent professional experience
- Specialized training or certifications in generative artificial intelligence red teaming, adversarial machine learning, artificial intelligence security, cybersecurity, responsible artificial intelligence, or artificial intelligence governance
- Experience designing and operationalizing trust and safety testing programs for large-scale consumer platforms, including escalation workflows, issue triage, and remediation tracking
- Experience working with product, legal, policy, and engineering stakeholders to translate risk findings into practical platform controls and governance improvements
The wage range for this role takes into account the wide range of factors that are considered in making compensation decisions including but not limited to skill sets; experience and training; licensure and certifications; and other business and organizational needs. The disclosed range estimate has not been adjusted for the applicable geographic differential associated with the location at which the position may be filled. At Deloitte, it is not typical for an individual to be hired at or near the top of the range for their role and compensation decisions are dependent on the facts and circumstances of each case. A reasonable estimate of the current range is $134,500 to $265,100.
You may also be eligible to participate in a discretionary annual incentive program, subject to the rules governing the program, whereby an award, if any, depends on various factors, including, without limitation, individual and organizational performance.
#CyberDTP27
Cyber Digital Trust and Online Safety Manager
The Digital Trust & Online Protection Professional will advise clients in developing, managing, and implementing policies, procedures, and strategies to ensure a safe, compliant, and trustworthy environment for our users. This individual will scale and mature digital trust and safety processes, including content compliance, user protection, and regulatory adherence across our platforms for our clients. Working closely with cross-functional stakeholders, this role will monitor regulatory changes, manage risks, and enhance our organization's approach to content safety, user trust, and online integrity.
Recruiting for this role ends on 12/31/3026.
Work you'll do
As a Manager, Strategy, Growth, and Transformation on the Deloitte Cyber team, you will be responsible for:
- Designing and executing testing scenarios to identify how prompts or user inputs could be manipulated to generate harmful, misleading, or misaligned generative artificial intelligence outputs.
- Researching emerging prompt injection, jailbreak, and adversarial testing techniques to evaluate model weaknesses, bias, factual inaccuracy, and misalignment with user intent.
- Assessing the effectiveness of content moderation systems in detecting unsafe outputs and documenting vulnerabilities, failure patterns, and potential misuse impacts.
- Recommending improvements to moderation policies, flagging mechanisms, training data, and governance controls based on testing findings.
- Collaborating with generative artificial intelligence development, content moderation, and cross-functional stakeholders to strengthen security, trust, safety, and responsible use outcomes.
- Developing multimodal test content and novel prompt manipulation methods to identify failure modes across text and other model inputs.
A successful candidate would possess these skills:
- Ability to work independently and collaborate as part of a team
- Effective written and verbal communication skills
- Meticulous attention to detail and quality of work product
- Ability to build and sustain professional relationships
- Ability to lead projects or workstreams
- Ability to manage and prioritize multiple tasks in a fast-paced and dynamic environment
- Strong interpersonal skills and professional demeanor
- Ability to meet deadlines
- Ability to mentor and provide clear guidance to others
The team
Enables trust and safety of online communications and digital products, protecting users, consumers, and patients from harm. Enables clients to provide consumer confidence in knowing with whom they are dealing and ensuring the integrity of access to data.
Qualifications
Required:
- Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Cybersecurity, Linguistics, Psychology, or a related field, or equivalent professional experience
- 10+ years of experience in threat modeling and simulation, prompt generation and analysis, novel testing, and reporting and improvement
- Demonstrated hands-on experience, portfolio work, publications, or research in prompt injection, jailbreak testing, model evaluation, adversarial machine learning, multimodal artificial intelligence safety, or generative artificial intelligence vulnerability assessment
- Ability to travel 25-50%, on average, based on the work you do and the clients and industries/sectors you serve.
- Limited immigration sponsorship may be available.
Preferred:
- Doctor of Philosophy (PhD) in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Cybersecurity, Linguistics, Psychology, or a related field, or equivalent professional experience
- Specialized training or certifications in generative artificial intelligence red teaming, adversarial machine learning, artificial intelligence security, cybersecurity, responsible artificial intelligence, or artificial intelligence governance
- Experience designing and operationalizing trust and safety testing programs for large-scale consumer platforms, including escalation workflows, issue triage, and remediation tracking
- Experience working with product, legal, policy, and engineering stakeholders to translate risk findings into practical platform controls and governance improvements
The wage range for this role takes into account the wide range of factors that are considered in making compensation decisions including but not limited to skill sets; experience and training; licensure and certifications; and other business and organizational needs. The disclosed range estimate has not been adjusted for the applicable geographic differential associated with the location at which the position may be filled. At Deloitte, it is not typical for an individual to be hired at or near the top of the range for their role and compensation decisions are dependent on the facts and circumstances of each case. A reasonable estimate of the current range is $134,500 to $265,100.
You may also be eligible to participate in a discretionary annual incentive program, subject to the rules governing the program, whereby an award, if any, depends on various factors, including, without limitation, individual and organizational performance.
#CyberDTP27