Unlock Full Resume Report

New offer - be the first one to apply!

September 3, 2026

Senior Security Engineer - Akamai Inference Cloud - Remote/Poland

Senior • Remote

Krakow, MA, Poland

Do you want to secure the runtime systems that execute AI models at global scale?

Are you passionate about defending inference infrastructure against emerging threats unique to AI workloads?

The Inference Execution & Runtimes team owns the core inference engine, including runtime frameworks, model-serving infrastructure, and execution environments that process every request. Its work determines the latency, throughput, and efficiency of AI workloads across global infrastructure.

Description

A Senior Security Engineer defines and implements security practices across the AI inference stack. Responsibilities include runtime hardening, supply-chain integrity, and threat modeling for inference workloads. This role requires security-engineering expertise and knowledge of AI/ML serving architectures, model execution environments, and their specific attack surfaces.

Responsibilities

  • Design and implement runtime security controls that protect inference execution environments against adversarial inputs, model extraction, and unauthorized access.
  • Conduct threat modeling and security assessments of inference-serving frameworks, model-loading pipelines, and GPU execution environments.
  • Harden model-serving infrastructure, including container isolation, runtime sandboxing, and supply-chain integrity for model artifacts and dependencies.
  • Develop automated security testing and monitoring for inference workloads to detect anomalous behavior, data exfiltration, and prompt-based attacks.
  • Collaborate with platform and model intelligence teams to establish security standards across the full inference lifecycle, from model ingestion to production serving.

Qualifications

  • Relevant experience in this area.
  • Hands-on experience in application or infrastructure security engineering, focused on runtime protection, threat modeling, or penetration testing.
  • Knowledge of AI/ML inference architectures and security challenges such as model poisoning, prompt injection, and data leakage.
  • Experience with container security, supply-chain hardening, and secure deployment practices in cloud-native environments.
  • Proficiency in Python, Go, or C++ and experience building security tooling or automated vulnerability detection.
  • Familiarity with security frameworks and compliance standards relevant to AI systems, such as OWASP ML Top 10, NIST AI RMF, and FedRAMP.

Benefits

Benefits support health, well-being, finances, and life beyond work.

FlexBase adapts to the job's needs. Employees can work at home, in an office, or in a combination of both.

Similar jobs you might like