F

Firmus Technologies

Designs and operates AI GPU data-centers.

Senior AI Security Engineer

Security Engineering & ArchitectureConfirmed live in the last 24 hours
Full-timeNo salary listed

About the Job

Requirements

  • At least 5 years of experience in security engineering, application security, cloud security, platform security, or a related field.
  • Demonstrated experience embedding security practices into software engineering or product-development teams and supporting secure delivery from design through production.
  • Strong understanding of application security, API security, secure software development lifecycle practices, threat modeling, vulnerability management, and security automation.
  • Practical understanding of AI and large language model application security risks, including prompt injection, indirect prompt injection, jailbreaks, insecure tool use, excessive agency, model abuse, sensitive-data exposure, cross-tenant data leakage, and supply-chain risks.
  • Experience securing agentic applications, retrieval-augmented generation systems, enterprise search, vector databases, model-serving APIs, enterprise-data connectors, or comparable AI-enabled systems.
  • Experience designing identity and access controls using OpenID Connect, OAuth 2.0, single sign-on, role-based access control, attribute-based access control, workload identity, service accounts, secrets management, and least-privilege principles.
  • Strong knowledge of Kubernetes and container security, including admission controls, network policies, role-based access control, runtime protection, image scanning, software supply-chain security, and policy engines.
  • Experience with secure continuous integration and continuous delivery, dependency governance, software bills of materials, image signing, provenance, artifact management, and controlled-release processes.
  • Proficiency in Python, Go, or a similar language for automation, security tooling, integrations, and analysis.
  • Familiarity with cloud and infrastructure security, including logging, monitoring, incident response, encryption, key management, and security controls for multi-tenant systems.
  • Knowledge of security and compliance frameworks such as NIST, ISO 27001, SOC 2, CIS Controls, OWASP ASVS, OWASP API Security Top 10, or equivalent frameworks.

Responsibilities

  • Partner with AI product, application, and engineering teams from discovery through production to define secure-by-design architectures for AI-powered products and services.
  • Threat-model large language model-enabled and agentic workflows, including direct and indirect prompt injection, data exfiltration, unsafe tool use, excessive agent permissions, cross-tenant access, model abuse, and unintended autonomous actions.
  • Design secure patterns for agent identity, delegated authorization, scoped credentials, tool allowlists, approval gates, action validation, execution sandboxing, rollback, and auditability.
  • Secure retrieval-augmented generation and enterprise-knowledge workflows, including document ingestion, indexing, retrieval permissions, metadata filtering, source attribution, tenant isolation, sensitive-data classification, and data-retention controls.
  • Define security controls for user-facing AI products, including authentication, authorization, consent, rate limiting, abuse detection, content and output controls, conversation-data handling, and customer-facing audit trails.
  • Secure model-serving and inference APIs through workload identity, API authentication, tenant-aware access controls, quotas, request validation, model access policies, usage monitoring, and logging controls.
  • Build reusable AI security guardrails, libraries, reference architectures, templates, policy-as-code, and developer tooling that make secure implementation the default path for product teams.
  • Work with DevOps and Platform teams to ensure Kubernetes, custom job-scheduler integrations, continuous integration and continuous delivery pipelines, secrets management, containers, and runtime environments provide the required security posture for AI applications.
  • Lead vulnerability management for AI application dependencies, model-serving runtimes, agent frameworks, software development kits, APIs, containers, CUDA and GPU software components, and related infrastructure.
  • Embed security requirements into application design reviews, pull-request and continuous-integration and continuous-delivery controls, release processes, operational runbooks, and incident-response procedures.
  • Develop security telemetry and detections for anomalous agent actions, unsafe tool calls, unusual data retrieval, credential misuse, inference API abuse, suspicious workload behavior, and policy violations.
  • Act as the principal security liaison between AI & Applications and the Cybersecurity function, coordinating architecture reviews, security exceptions, risk acceptance, compliance evidence, incident response, and remediation tracking.

About the Company

Firmus Technologies

Designs and operates AI GPU data-centers.

Firmus Technologies builds AI-focused data centers called the AI factory, featuring liquid-cooled GPU campuses and a GPU cloud. Its AI FactoryOS ties cooling, racks, and chips together to maximize uptime and throughput. It differentiates with a full hardware–software stack for AI, MLPerf efficiency data, NVIDIA partnerships, and renewable-powered campuses such as Tasmania’s Green AI Factory Zone. Its goal is to scale energy-efficient, sovereign AI infrastructure for tens of thousands of GPUs while reducing costs and boosting AI throughput.

Company size
51-200
Company stage
IPO
Headquarters
Launceston, Australia
Founded
2019

Recently Posted Jobs

Explore more opportunities at Firmus Technologies

See more jobs