Sr AI Engineer, Security

Realtor.com is building and securing an AI platform that spans both AWS and GCP, with a focus on real-world protections for AI workloads, agents, and data flows. As a Sr AI Engineer, Security, you will design guardrails, strengthen the AI supply chain, and help prepare the organization to detect and respond to AI-specific incidents, while partnering closely with News Corp’s cybersecurity team.

What you’ll do

• Design and enforce AI workload guardrails on AWS (Bedrock, Lambda, IAM, KMS, SCPs, GuardDuty, Security Hub) and GCP (Vertex AI, IAM, VPC Service Controls, Org Policies, Security Command Center, Cloud KMS).
• Define agent and non-human account identity and authorization using short-lived, narrowly scoped credentials, delegated user permissions, and a per-agent audit trail to limit blast radius.
• Build agent containment with separated read and write permissions, network egress controls, sandboxed execution, approval gates for high-risk actions, and kill switches.
• Create an agent gateway or control plane that keeps agents and tool calls within approved limits.
• Secure the AI supply chain by scanning where models come from (including unsafe formats like pickle), vetting models and datasets from public hubs such as Hugging Face, and maintaining an AI-BOM inventory of models, data, and tools per system. Include an approval process for new MCP servers and agent tools.
• Defend against prompt injection, tool poisoning, RAG poisoning, and sensitive data leakage.
• Implement detection and logging for agent and model activity, and own AI-specific incident response playbooks.
• Lead threat modeling for new products, features, internal solutions, and agent workflows. Apply frameworks such as STRIDE, the OWASP LLM/GenAI Top 10, MITRE ATLAS, and OWASP ASVS, then translate findings into design requirements and release criteria.
• Review pull requests, architecture designs, and release readiness across apps to agent fleets, providing concrete recommendations that unblock delivery.
• Build secure-by-default frameworks including paved-road frameworks, reference architectures, and templates that prevent entire categories of risk.
• Harden CI/CD with secrets scanning, SAST/SCA, GitHub Actions hardening, and policy-as-code in Terraform.
• Run ongoing red-team and evaluation activities for models, agents, and LLM apps, including testing new AI features before launch.
• Partner with News Corp’s global cybersecurity team to align Realtor.com’s AI and cloud security with group-wide standards, policies, and risk frameworks.
• Coordinate incident response, threat intelligence, and vulnerability disclosure across News Corp businesses.
• Share AI security patterns, threat models, and lessons learned with other News Corp teams, bringing those insights back to Realtor.com.
• Build security-focused agents to triage findings, investigate alerts, audit IAM for least privilege, and open tested, secure-by-default fix pull requests.
• Use Claude Code, Devin, and MCP to make the security team faster and share those patterns across engineering teams.
• Track emerging AI threats, incidents, research, and vendor capabilities, converting new attack techniques, releases, and framework updates (including OWASP, MITRE ATLAS, and others) into platform actions.
• When a major industry incident occurs, assess exposure and lead response efforts.
• Prototype new approaches through small experiments, measure outcomes, and promote what works into platform standards.
• Write internal briefings and recommend when to adopt, pilot, or skip tools and practices.
• Create and run AI security training for engineers, product teams, and the wider company, including prompt injection, data leakage, excessive agency, and secure use of Claude, Glean, Devin, and Gemini.
• Act as the security voice in AI platform strategy by evaluating vendors and models, defining production readiness, and supporting AI governance across the AI lifecycle.
• Brief leadership on AI risk and where to invest, and represent Realtor.com externally via conference talks, open-source work, or industry working groups.

Required qualifications

• 5+ years in cybersecurity, cloud security, AppSec/product security, or security platform engineering.
• Hands-on depth in AWS security plus real experience in GCP (or strong multi-cloud background).
• A security mindset focused on permissions, scopes, logs, approval gates, data boundaries, and rollback, rather than relying on “do not” instructions.
• Experience securing LLM or agentic systems, including prompt injection defenses, retrieval and data-boundary risks, agent identity, and model/tool supply-chain integrity.
• Threat modeling experience for products and platforms, with ability to lead sessions and turn outcomes into requirements.
• Hands-on experience building with agents, tool calling, or MCP, plus AI coding tools.
• Strong code-review skills in at least one of Python, TypeScript, or Go, and comfort with Terraform/IaC.
• Experience with zero trust, least privilege, SSO/OIDC/OAuth, secrets management, and vulnerability management.
• Experience working within a larger security organization (parent company or federated model) and balancing alignment with local execution speed.
• Ability to follow AI security research and incident write-ups and apply recent learnings.
• A builder’s mindset: comfortable prototyping controls and working where playbooks do not yet exist.
• Strong communication skills to explain risk to audiences ranging from PR comments to executive briefings and company-wide training.

Technologies you’ll work with

• AWS, GCP, Bedrock, Lambda, IAM, KMS, SCPs, GuardDuty, Security Hub, Vertex AI, VPC Service Controls, Org Policies, Security Command Center, Cloud KMS
• Hugging Face, MCP, Claude Code, Devin, Claude, Glean, Gemini
• Threat modeling and security frameworks: STRIDE, OWASP LLM/GenAI Top 10, MITRE ATLAS, OWASP ASVS, OWASP
• Engineering and automation: Terraform, CI/CD, GitHub Actions, SAST/SCA, Python, TypeScript, Go
• Security concepts: zero trust, least privilege, SSO/OIDC/OAuth, secrets management, Terraform/IaC, AI-BOM
• AI risk topics: pickle, RAG, RAG poisoning

Benefits

• Inclusive and competitive medical, Rx, dental, and vision coverage
• Family forming benefits
• 13 paid holidays
• Flexible time off
• 8 hours of paid volunteer time off
• Immediate eligibility into Company 401(k) plan with 3.5% company match
• Tuition Reimbursement program for degreed and non-degreed programs
• 1:1 personalized Financial Planning Sessions
• Student Debt Retirement Savings Match program
• Free snacks and refreshments in each office location

Nice to have

• AWS Security Specialty, Google Professional Cloud Security Engineer, CCSP, CISSP, OSCP, or GIAC (GCSA/GWEB)
• Experience red-teaming or evaluating AI models or agents
• Familiarity with NIST AI RMF, ISO 42001, Google SAIF, CoSAI, NIST SSDF, or the EU AI Act
• Experience securing Snowflake (RBAC, masking, network policy)
• Conference talks, published research, or open-source security contributions

Location and work style

• Austin, TX (onsite)
• In-person collaboration is emphasized, with employees working four or more days in the office for most roles.