As the advertising ecosystem expands, sophisticated adversarial actors are leveraging generative AI, automation, and distributed infrastructure to bypass safety controls. The Ads Trust and Safety team requires a Principal Applied Scientist to contribute to the research and technical strategy for Threat Modelling team. We are looking for a security domain expert who can advance the state of the art in Threat Modeling, and Adversarial Defense. This role involves transitioning trust mechanisms from static verification to dynamic, behavioural-based integrity systems. You will architect solutions to detect and neutralize high-complexity fraud vectors, such as phishing, payment fraud, cloaking, malware distribution, token misuse, and authentication, ensuring the ads platform remains safe for users, advertisers, and publishers. The primary success metric is the robust identification and mitigation of advanced abuse vectors with minimal impact on legitimate advertiser friction and ad-serving latency.
\nResponsibilities:
\nStrategic Threat Modeling: Develop and maintain comprehensive adversarial frameworks to map the lifecycle of emerging threats, from account compromise (ATO) to malicious payload delivery.
\nEvolution of Advertiser Trust: Advance the continuous, signal-based security protocol. Research and implement behavioural biometrics and Proof of Liveness models to detect synthetic identities and coordinated fraud rings.
\nAdversarial Research: Proactively identify 'unknown unknown' vulnerabilities through red-teaming and exploratory data analysis, developing models to predict attacker behaviour before widespread exploitation.
\nTechnical Leadership: Drive the technical roadmap for integrity and security, mentoring senior engineers and influencing cross-functional stakeholders on security investment priorities.
\nQualifications:
\nBachelor's, Master's, or PhD degree in Computer Science, Cybersecurity, Mathematics, or a related field, with 10+ years of related experience.
\nDeep technical expertise in Cybersecurity, Anti-Abuse, or Adversarial Machine Learning.
\nStrong programming skills in C++ or Python (at least one is required), with experience in building production-quality security or ML systems.
\nHands-on experience in one or more of the following: Web Security standards and Authentication Protocols (OAuth, OIDC).
\nMalware analysis, de-obfuscation, or reverse engineering.
\nBuilding fraud detection models at scale.
\nProven ability to design and implement defence mechanisms against complex abuse vectors (e.g., botnets, synthetic identity, evasion/cloaking).
\nStrong communication and collaboration skills, with experience articulating complex security risks to business and product leadership.
\nPreferred Qualifications:
\n5+ years of experience in an Adversarial/Trust & Safety role at a major internet platform or cybersecurity firm.
\nFamiliarity with the Ad-Tech stack (RTB, OpenRTB) and associated fraud incentives.
\nBackground in Graph Neural Networks (GNNs) for fraud ring detection or behavioural biometrics.
\nTrack record of impact via security research publications, patents, or contributions to industry security standards.
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_b5d2dd81-5ff","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Microsoft","sameAs":"https://microsoft.ai","logo":"https://logos.yubhub.co/microsoft.ai.png"},"x-apply-url":"https://microsoft.ai/job/principal-applied-scientist-33/","x-work-arrangement":"onsite","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["Cybersecurity","Anti-Abuse","Adversarial Machine Learning","C++","Python","Web Security standards","Authentication Protocols","Malware analysis","De-obfuscation","Reverse engineering","Fraud detection models"],"x-skills-preferred":["Graph Neural Networks","Behavioural biometrics"],"datePosted":"2026-04-24T12:13:01.732Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Bengaluru"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Cybersecurity, Anti-Abuse, Adversarial Machine Learning, C++, Python, Web Security standards, Authentication Protocols, Malware analysis, De-obfuscation, Reverse engineering, Fraud detection models, Graph Neural Networks, Behavioural biometrics"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_d63f049e-ad7"},"title":"Security Lead, Agentic Red Team","description":"Job Title: Security Lead, Agentic Red Team
\nWe're a team of scientists, engineers, and machine learning experts working together to advance the state of the art in artificial intelligence. Our mission is to close the 'Agentic Launch Gap'; the critical window where novel AI capabilities outpace traditional security reviews.
\nAs the Security Lead for the Agentic Red Team, you will direct a specialized unit of AI Researchers and Offensive Security Engineers focused on adversarial AI and agentic exploitation. Operating as a technical player-coach, you will architect complex, multi-turn attack scenarios while managing cross-functional partnerships with Product Area leads and Google security to influence launch criteria.
\nKey Responsibilities:
\nAbout You:
\nIn addition, the following would be an advantage:
\nThe US base salary range for this full-time position is between $248,000 - $349,000 + bonus + equity + benefits.
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_d63f049e-ad7","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Google DeepMind","sameAs":"https://deepmind.com/","logo":"https://logos.yubhub.co/deepmind.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/deepmind/jobs/7560787","x-work-arrangement":"onsite","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$248,000 - $349,000 + bonus + equity + benefits","x-skills-required":["Bachelor's degree in Computer Science, Information Security, or equivalent practical experience","Experience in Red Teaming, Offensive Security, or Adversarial Machine Learning","Deep technical understanding of LLM architectures and agentic workflows","Proven ability to work in a consulting capacity with product teams","Experience managing or technically leading small, high-performance engineering teams"],"x-skills-preferred":["Hands-on experience developing exploits for GenAI models","Familiarity with AI safety benchmarks and evaluation frameworks","Experience writing code (Python, Go, or C++) to build automated security tools or fuzzers","Ability to communicate complex probabilistic risks to executive stakeholders and engineering teams effectively"],"datePosted":"2026-03-16T14:41:55.843Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Mountain View, California, US; New York City, New York, US"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Bachelor's degree in Computer Science, Information Security, or equivalent practical experience, Experience in Red Teaming, Offensive Security, or Adversarial Machine Learning, Deep technical understanding of LLM architectures and agentic workflows, Proven ability to work in a consulting capacity with product teams, Experience managing or technically leading small, high-performance engineering teams, Hands-on experience developing exploits for GenAI models, Familiarity with AI safety benchmarks and evaluation frameworks, Experience writing code (Python, Go, or C++) to build automated security tools or fuzzers, Ability to communicate complex probabilistic risks to executive stakeholders and engineering teams effectively","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":248000,"maxValue":349000,"unitText":"YEAR"}}},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_f73f108d-30a"},"title":"Senior Security Engineer, Agentic Red Team","description":"Job Title: Senior Security Engineer, Agentic Red Team
\nWe're a team of scientists, engineers, machine learning experts, and more, working together to advance the state of the art in artificial intelligence.
\nAbout Us The Agentic Red Team is a specialized, high-velocity unit within Google DeepMind Security. Our mission is to close the 'Agentic Launch Gap',the critical window where novel AI capabilities outpace traditional security reviews.
\nThe Role As a Senior Security Engineer on the Agentic Red Team, you will be the primary technical executor of our adversarial engagements. You will work 'in the room' with product builders, identifying architectural flaws during the design phase long before formal reviews begin.
\nKey Responsibilities:
\nAbout You In order to set you up for success as a Software Engineer at Google DeepMind, we look for the following skills and experience:
\nPreferred Qualifications
\nSalary & Benefits The US base salary range for this full-time position is between $166,000 - $244,000 + bonus + equity + benefits.
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_f73f108d-30a","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Google DeepMind","sameAs":"https://deepmind.com/","logo":"https://logos.yubhub.co/deepmind.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/deepmind/jobs/7596438","x-work-arrangement":"onsite","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$166,000 - $244,000 + bonus + equity + benefits","x-skills-required":["Python","Go","C++","Red Teaming","Offensive Security","Adversarial Machine Learning","LLM architectures","agentic workflows","chain-of-thought reasoning","AI vulnerability classes"],"x-skills-preferred":["prompt injection","adversarial examples","training data extraction","AI safety benchmarks","evaluation frameworks","fuzzing techniques"],"datePosted":"2026-03-16T14:39:43.939Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Mountain View, California, US; New York City, New York, US; Zurich, Switzerland"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Go, C++, Red Teaming, Offensive Security, Adversarial Machine Learning, LLM architectures, agentic workflows, chain-of-thought reasoning, AI vulnerability classes, prompt injection, adversarial examples, training data extraction, AI safety benchmarks, evaluation frameworks, fuzzing techniques","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":166000,"maxValue":244000,"unitText":"YEAR"}}},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_716d3247-e3f"},"title":"ML/Research Engineer, Safeguards","description":"About Anthropic
\nAnthropic's mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
\nAbout the role
\nWe are looking for ML Engineers and Research Engineers to help detect and mitigate misuse of our AI systems. As a member of the Safeguards ML team, you will build systems that identify harmful use—from individual policy violations to sophisticated, coordinated attacks—and develop defenses that keep our products safe as capabilities advance. You will also work on systems that protect user wellbeing and ensure our models behave appropriately across a wide range of contexts. This work feeds directly into Anthropic's Responsible Scaling Policy commitments.
\nResponsibilities
\nYou may be a good fit if you
\nStrong candidates may also have experience with
\nLogistics
\nEducation requirements: We require at least a Bachelor's degree in a related field or equivalent experience. Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
\nVisa sponsorship
\nWe do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.
\nWe encourage you to apply even if you do not believe you meet every single qualification.
\nNot all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work.
\nYour safety matters to us.
\nTo protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.
\nHow we're different
\nWe believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.
\nThe easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.
\nCome work with us!
\nAnthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_716d3247-e3f","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Anthropic","sameAs":"https://job-boards.greenhouse.io","logo":"https://logos.yubhub.co/anthropic.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/anthropic/jobs/4949336008","x-work-arrangement":"hybrid","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":"$350,000 - $500,000USD","x-skills-required":["Python","Machine Learning","Research Engineering","Adversarial Machine Learning","Red-teaming","Interpretability","Probes","Reinforcement Learning","High-performance, large-scale ML systems"],"x-skills-preferred":["Language modeling and transformers","Building classifiers, anomaly detection systems, or behavioral ML"],"datePosted":"2026-03-08T13:46:45.711Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA | New York City, NY"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, Machine Learning, Research Engineering, Adversarial Machine Learning, Red-teaming, Interpretability, Probes, Reinforcement Learning, High-performance, large-scale ML systems, Language modeling and transformers, Building classifiers, anomaly detection systems, or behavioral ML","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":350000,"maxValue":500000,"unitText":"YEAR"}}}]}