Job Description: 
About CENSUS CENSUS is a globally recognized cybersecurity services provider that serves the needs of numerous industries by offering IT and OT security services to public and private organizations worldwide, including Fortune 500 companies, financial institutions, critical infrastructure, automotive, and secure communications. Driven by state-of-the-art research, scientific analysis, and extensive engineering experience across a variety of industries and technologies, CENSUS provides unmatched security consulting & assessment services for products (software, services, devices, and large-scale platforms), infrastructure, and organizations.
About the Job / Key Responsibilities:
In this strategic role, you will use your knowledge of AI/ML Security to help our clients reach their cybersecurity objectives by guiding them toward safe and effective strategies, architectures, and integrations. About the Job / Key Responsibilities We are seeking bright and driven professionals to join our Product Security Professional Services team and support our mission to deliver top-tier cybersecurity services and solutions.
. Working with cross-functional teams and leading a group of security engineers and consultants, you will be a key contributor on projects that include: Secure Data Handling and Processing: Create and evaluate secure data handling procedures throughout the model lifecycle, including data collection, preprocessing, storage, and usage, to avoid unauthorized access and data leakage; 
. End-to-End System Integrity & Trustworthiness: Design & assess architectures and implementations that ensure integrity across the entire system, ensuring that data, models, and outputs are reliable and accurately reflect user inputs and real-world conditions.
. Designing comprehensive security solutions that safely integrate AI into the larger product ecosystem while adhering to client demands and legal constraints is the technical strategy and solution design.
Among your daily responsibilities will be:
. developing, evaluating, and extending safe AI frameworks, architectures, and solutions for edge and cloud/backend systems.
. helping to gather, translate, and improve the security needs for AI-powered systems and solutions.
. investigating, evaluating, contrasting, and suggesting technologies that meet the client's specified needs while complementing their business plans.
. examining the security designs of products, recording the absence of security safeguards, and promoting analysis to enhance security.
. organizing, carrying out, and overseeing end-to-end security posture evaluations using functional testing, fuzz testing, source code audits, and other relevant techniques.
. confirming that the output implementation complies with the requirements, threat model, and security architecture of the goods.
. use both technical and business-oriented language when documenting and discussing product security threats.
Minimum Requirements:
. A master's or bachelor's degree in computer science, information security, artificial intelligence (AI/ML), computer engineering, or a related field of work.
. eight or more years of cybersecurity expertise, with at least three of those years spent concentrating on machine learning engineering, AI security, or safe software design for AI/ML-powered applications.
. shown expertise in developing and deploying reliable and secure AI solutions in intricate, cross-functional settings for more than two years.
strong communication abilities and fluency in English.
Required Skills:
. Proficiency in programming languages like Python, Java, Scala, or C++, familiarity with AI/ML libraries and frameworks (e.g., TensorFlow, PyTorch, Scikit-learn), 
. knowledge of threat modeling, secure data management, and AI-specific privacy-preserving techniques, and familiarity with applied cryptography and cryptographic protocols, such as E2E protection, authenticated encryption, Key Exchange / Agreement, Secure Multi-Party Computation, and Federated Learning with Encryption, are all necessary.
Desired Capabilities:
. knowledge of specific frameworks like TensorFlow Lite, PyTorch Mobile, Core ML (iOS), and Qualcomm's SNPE for implementing AI at the edge.
. Comprehending edge device hardware accelerators such as GPUs, Google's TPUs, and neural processing units (NPUs).
. knowledge of platforms and technologies like Google Cloud IoT, Azure IoT Edge, and AWS IoT Greengrass for building and tracking AI models on edge devices.
. knowledge of virtualization, enclaves, containers, attestation technologies, and confidential computing.
. leading a group of security experts and consultants in the evaluation and investigation of cutting-edge goods and technology.