Responsibilities

• Design and implement secure boot and firmware integrity mechanisms for AI-capable embedded platforms
• Develop and apply runtime hardening and isolation strategies for machine-learning workloads
• Enable model protection using Trusted Execution Environments (TEE), secure enclaves, or comparable trust technologies
• Ensure the secure loading, verification, and execution of ML models on edge devices
• Contribute to security architecture decisions covering the full stack from firmware to application runtime
• Collaborate with platform, architecture, and research teams to evolve prototype solutions into reusable technical concepts

Profile

• Strong background in Embedded Systems, Cybersecurity, or Cryptography with a clear interest in applied Machine Learning or Background in Machine Learning with a strong focus on system-level or platform security
• Solid hands-on experience in embedded software development using C/C++ (Rust is a plus but not mandatory)
• In-depth understanding of secure boot, firmware security, and runtime protection mechanisms
• Experience with, or strong interest in, Trusted Execution Environments (TEE), secure enclaves, TPM/HSM-like components
• Basic familiarity with machine-learning model formats and deployment workflows on embedded or edge platforms
• Sound knowledge of cryptographic primitives and their application for integrity, authenticity, and confidentiality

Benefits

• Freelance / contract-based engagement
• Innovation-driven, prototype-focused environment
• High technical depth with emphasis on security engineering rather than product maintenance
• Well suited for senior engineers or consultants with a strong embedded and security background looking to work in an AI context

‍