AI Security Engineer – Technical Lead

About CENSUS

CENSUS is an internationally acclaimed Cybersecurity services provider. We support the needs of multiple industries, providing IT and OT security services to public and private organizations around the world, ranging from financial institutions and critical infrastructure to automotive and secure communications, including Fortune 500 companies. Powered by cutting-edge research, scientific analysis and in-depth engineering experience across various industries & technologies, CENSUS delivers unparalleled security consulting & assessment services for products (software, services, devices, and large-scale platforms), infrastructure, and organizations.

Learn more about CENSUS at census-labs.com.

About the Job / Key Responsibilities

We are looking for talented and ambitious professionals to join our Product Security Professional Services team and support our mission to deliver top-tier cybersecurity services and solutions. In this strategic role, you’ll leverage your expertise in the AI/ML Security domain to guide our clients towards secure and efficient strategies, architectures, and integrations, helping them achieve their cybersecurity goals.

As a key contributor, you’ll collaborate with cross-functional teams and manage a team of security engineers and consultants in projects that involve:

• End-to-End System Integrity & Trustworthiness: Design & assess architectures and implementations that ensure integrity across the entire system, making sure data, models, and outputs are trustworthy and accurately reflect user inputs and real-world conditions.

• Secure Data Handling and Processing: Design and assess secure data handling practices throughout the model lifecycle, including data collection, preprocessing, storage, and usage, to prevent unauthorized access and data leakage.

• Technical Strategy and Solution Design: Design comprehensive security solutions that incorporate AI securely within the broader product ecosystem, aligning them with both client requirements and regulatory standards.

Your day-to-day duties will include:

• Creating, reviewing, and expanding secure AI architectures, frameworks and solutions on both cloud / backend and edge systems.

• Assisting in the collection, technical translation, and fine-tuning of security requirements of AI-powered solutions and systems.

• Researching, reviewing, comparing, and proposing technologies that can satisfy the client’s established requirements, and aligning with their strategies.

• Reviewing product security designs, documenting missing security controls, and driving analysis for security improvements.

• Planning, executing, and supervising end-to-end security posture assessments via source code auditing, functional testing, fuzz testing and other applicable methodologies.

• Verifying if output implementation is aligned with the products’ security architecture, requirements, and threat model.

• Documenting and presenting product security risks in both technical and business-oriented language.
  

Minimum Qualifications

• MSc or BSc in Computer Science, Information Security, AI/ML, Computer Engineering, or equivalent practical experience.

• 8+ years of experience in Cybersecurity with at least 3+ years specifically in AI security, machine learning engineering, or secure software architecture for AI/ML powered solutions.

• Proven experience of 2+ years in designing and implementing trustworthy and secure AI solutions within complex, cross-functional environments.

• Proficient in English and excellent communication skills.

Required Skills

• In-depth understanding of AI/ML security, including adversarial machine learning, data integrity, and model robustness.

• Proficiency in programming languages such as Python, Java, Scala or C++, and familiarity with AI/ML libraries and frameworks (e.g., TensorFlow, PyTorch, Scikit-learn).

• Extensive, and leading role experience with producing & reviewing platform security architecture.

• Experience with threat modeling, secure data management, and privacy-preserving techniques specific to AI.

• Experience with applied cryptography and cryptographic protocols, such as E2E protection, authenticated encryption, Key Exchange / Agreement, Secure Multi-Party Computation, and Federated Learning with Encryption.

• Hands-on experience with securing AI/ML deployments on cloud platforms (e.g., AWS, Azure, GCP) and understanding of cloud-native security practices.

• Excellent leadership, ownership, problem solving skills, and willingness to learn/grow.

Nice-to-have Skills

• Familiarity with specialized frameworks for deploying AI at the edge, such as TensorFlow Lite, PyTorch Mobile, Core ML (iOS), and Qualcomm’s SNPE.

• Understanding hardware accelerators like GPUs, Google’s TPUs, and neural processing units (NPUs) for edge devices.

• Familiarity with platforms and tools for deploying and monitoring AI models on edge devices, such as AWS IoT Greengrass, Azure IoT Edge, and Google Cloud IoT.

• Familiarity with confidential computing, virtualization, enclaves, containers, and attestation technologies.

• Managing a team of security engineers and consultants to successfully assess and research bleeding edge technologies and products.