2 Adversarial Ml Jobs

As an AI Governance Expert, your primary responsibility will be to establish and maintain a robust governance framework for the ethical, secure, and compliant use of AI technologies across the Digital Grid portfolio at Siemens Energy. You will collaborate closely with cybersecurity, data science, and product teams to ensure that AI systems are trustworthy, transparent, and in alignment with the sustainability and digitalization goals of Siemens Energy. Your role will involve developing and implementing AI governance policies, procedures, and controls that adhere to global standards such as the EU AI Act and NIST AI RMF. You will be tasked with identifying and mitigating risks associated with data and AI models, including issues related to bias, explainability, data privacy, and cybersecurity. Additionally, you will establish protocols for model documentation, validation, and monitoring throughout the AI lifecycle. Collaboration will be a key aspect of your role as you work with data scientists, engineers, and compliance teams to integrate data governance into AI development and deployment processes. You will also support internal and external audits related to AI systems to ensure compliance with regulatory and ethical standards. Conducting training sessions on responsible AI practices and governance for internal stakeholders will be part of your responsibilities. To excel in this role, you should hold a Bachelor's or Master's degree in computer science, data science, cybersecurity, business, or a related field. You must have 5 to 8 years of experience in GRC, cybersecurity, or data governance, with at least 2 years specifically in AI/ML governance or data management. A strong understanding of AI/ML technologies, data privacy laws, and risk frameworks like NIST AI RMF is required. Familiarity with regulatory frameworks such as the EU AI Act, EU Data Act, and EU CRA is also essential. Excellent communication, stakeholder engagement, and analytical skills are crucial for this role. Experience with AI model documentation, including Model Cards and Datasheets for Datasets, is preferred. Knowledge of adversarial ML, secure AI development, and MLOps will be beneficial. Certifications such as ISO/IEC 8000, ISO/IEC 42001, or equivalent would be an advantage.,

Job Description Do you want to lead teams that find and exploit security vulnerabilities in Fortune 100 companies, critical infrastructure, and public sector agencies impacting millions of users? Join Securins Offensive Security Team where you'll emulate real-world attacks and oversee advanced offensive operations. We are a cross-disciplinary group of red teamers, adversarial AI researchers, and software developers dedicated to finding and fixing vulnerabilities across critical digital ecosystems. Role & responsibilities - Lead and perform advanced offensive security assessments, including Red Team operations, threat-based evaluations, and vulnerability exploitation. - Supervise and mentor a team of offensive engineers, manage task prioritization, and ensure high-quality delivery. - Execute Red Team operations on production systems, including AI platforms, using real-world adversarial tactics. - Provide strategic and technical security guidance to internal and external stakeholders. - Collaborate cross-functionally to integrate findings into enterprise detection and defense strategies. - Research and develop adversary TTPs across the full attack lifecycle. - Build tools to automate and scale offensive emulation and vulnerability discovery, utilizing AI/ML systems. - Continuously evaluate and enhance assessment methodologies and frameworks used by the team. - Contribute to the security community through publications, presentations, bug bounties, and open-source projects. Required Qualifications - 5+ years of experience in offensive security, red teaming, or penetration testing with at least 1 year in a leadership role. - Bachelors or Masters degree in Computer Science, Computer Engineering, or relevant field; or equivalent experience. - Expert knowledge of offensive security tactics, threat modeling, APT emulation, and Red Team operations. - Strong understanding of MITRE ATT&CK framework and exploitation of common vulnerabilities. - Proficiency in one or more programming/scripting languages (Python, Go, PowerShell, C/C++, etc.). - Hands-on experience with penetration testing tools such as Metasploit, Burp Suite Pro, NMAP, Nessus, etc. - Familiarity with security in cloud environments (AWS, Azure, GCP) and across Windows/Linux/macOS platforms. - Ability to clearly articulate findings to technical and executive audiences and lead mitigation efforts. - Authorization to work in the country of employment at time of hire and ongoing during employment. Preferred Qualifications - Certifications like OSCP, OSCE, OSEP, CRTO, or equivalent. - Experience with Purple Team operations and threat intelligence integration. - Track record in CTF competitions or bug bounty programs. - Reverse engineering experience or malware analysis expertise. - Exposure to Responsible AI and adversarial machine learning. - Participation in AI Village at DEFCON or similar security research events. - Publications or contributions to conferences such as AISec, NeurIPS, FAccT, or IC4. Other Requirements Ability to meet Securin, customer, and/or government security screening requirements. This includes a background check at the time of hire/transfer and every two years thereafter. Who Should Apply You have experience executing technical research and offensive security strategies with teams. You are skilled in experimental security science and confident in building your own tools. You clearly communicate findings, are mission-driven, and want to drive change in AI and cybersecurity. Role-Specific Policy This hybrid role requires in-office presence at least 50% of the time. Locations: Chennai, Tamil Nadu (India)