Security Platform Automation Engineer

We are the Assurance Automation u0026 Risk Management team within Apple Services Engineering (ASE) Security org. We are responsible for securing the platforms infrastructure and distributed systems behind Apples global services including iCloud App Store Apple Music TV Maps and operates thousands of critical backend services across a rapidly expanding global footprint. We have a transformative opportunity to amplify security experts reach by building the next-generation AI-assisted Security Automation Platform. Rather than building isolated tooling we turn expert security standards into robust running software by combining agentic workflows deterministic scaffolding and rigorous evaluation gates integrated directly into Apples core security data systems (Security Findings Bill of Materials and Risk Governance).nnWe are hiring Tech Lead to lead the software architecture and agentic engineering of this platform. Your effort will help build solutions to a variety of outstanding security challenges in software supply chain security posture and risk management. Join us and youll play a meaningful role in ensuring the highest standard of security for one of the most-watched companies in the world.

Were looking for an exceptional automation engineer to build the pipeline that scales security review across Apples 1000s services. You will turn security expertise into running software designing and operating AI agentic review system skills tool layer evaluation harness on top of Apples existing security tooling and giving reviewers a reliable high-throughput pipeline to execute against. Youll partner closely with the security engineers who define the review standards and the analysts who validate the output and build automation that reduces toil.

Design system and interfaces that make Apples existing security systems agent-consumablenBuild and maintain the review automation pipeline that ingests a service runs AI-assisted threat modeling and triage and produces structured reviewable output at scalenImplement the AI skills and routing criteria defined by our security standards engineers meeting quality targets for precision recall and false positivesnIntegrate the pipeline with existing security engineering tooling (findings vulnerability intelligence SBOM scanning and risk-acceptance systems) rather than standing up parallel foundationsnBuild the quality feedback loop so signals from reviewer validation continuously improve the automationnBe accountable for quality software that meets service level objectives with runbooks tests and observability so no system depends on a single personnOwn prompt skill and model versioning as code with the eval gatesnResearch prototype and present ideas and designs to your team management and internal customers

1 year of building LLM- or agent-based systems that ran in production with a measured quality barn8 years building and operating production automation data pipelines or backend servicesnHighly proficient in at least one of Python Go or JavanExperience integrating third-party and first-party APIs tooling and services into reliable end-to-end workflows and AI agent workflowsnWorking knowledge of application and cloud security concepts (threat modeling vulnerabilities secure configuration)nMS or BS or equivalent experience in Computer Science Engineering or a related field OR equivalent practical experience in Software or Security Engineeringn

Experience with Agent engineering: retrieval grounding citation reasoningnExperience with Agentic workflow design with bounded autonomy building LLM- or agent-based automation and evaluating output quality (precision/recall human-in-the-loop feedback loops) AI agent evaluation harness as CInFamiliar with AWS cloud resources (S3 EC2 Lambda Step Functions etc.)nExperience with security tooling such as SAST/SCA scanners SBOM tooling or vulnerability intelligence platformsnBackground in security review threat modeling or supply-chain securitynExperience delivering tooling used by non-engineer reviewers or contractors at scalenAwareness of AI-specific threats in systems that ingest untrusted inputn