Sr AI Engineer, Security

Realtor.com is building security for AI platforms that operate across cloud environments and real-world agent workflows. In this role, you will design, validate, and operationalize AI security controls spanning AWS and GCP, with a focus on guardrails, supply-chain integrity, threat modeling, and incident readiness for LLM and agentic systems.

This is a hands-on security engineering position based in Austin, TX, onsite, requiring deep experience securing AI workloads and the ability to translate risk into practical design requirements, release criteria, and scalable standards.

Key responsibilities

• Design and enforce AI workload guardrails on AWS (Bedrock, Lambda, IAM, KMS, SCPs, GuardDuty, Security Hub) and on GCP (Vertex AI, IAM, VPC Service Controls, Org Policies, Security Command Center, Cloud KMS).
• Define how agents and other non-human accounts are identified and authorized using short-lived, narrowly scoped credentials, delegated user permissions, and a per-agent audit trail to limit potential blast radius from misbehavior.
• Build agent containment using separate 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 to keep agent behavior and tool calls within approved limits.
• Secure the AI supply chain by controlling model intake and scanning, including unsafe formats such as pickle, vetting models and datasets from sources like Hugging Face, and operating an approval process for new MCP servers and agent tools.
• Maintain an inventory of models, data, and tools used by each system via an AI-BOM, and apply defenses against prompt injection, tool poisoning, RAG poisoning, and sensitive data leakage.
• Implement detection and logging for agent and model activity, and take ownership of AI-specific incident response playbooks.
• Lead threat modeling for new products, features, and internal solutions, spanning consumer experiences through internal tools and agent workflows, using frameworks such as STRIDE, OWASP LLM/GenAI Top 10, MITRE ATLAS, and OWASP ASVS, then convert findings into design requirements and release criteria.
• Review pull requests, architecture designs, and release-readiness across apps and agent fleets, providing concrete suggestions that help teams move forward.
• Build “paved-road” frameworks, reference architectures, and secure-by-default templates that prevent entire categories of risk rather than relying on one PR at a time.
• Embed security into CI/CD with secrets scanning, SAST/SCA, GitHub Actions hardening, and policy-as-code in Terraform.
• Run an ongoing red-team and evaluation program for models, agents, and LLM apps, including testing AI features before launch.
• Align with News Corp’s global cybersecurity organization on standards, policies, and risk frameworks, and coordinate on incident response, threat intelligence, and vulnerability disclosure across businesses.
• Share AI security patterns, threat models, and lessons learned with other News Corp businesses and bring those insights back to Realtor.com.
• Build agents that support security work, including triage, alert investigation, IAM least-privilege auditing, and submitting tested, secure-by-default fix PRs.
• Use tools such as Claude Code, Devin, and MCP to accelerate security efforts and share approaches with other engineering teams.
• Track emerging AI threats, incidents, research, and vendor capabilities, turning them into concrete platform actions, including updates to OWASP and MITRE ATLAS as relevant.
• After major industry incidents, quickly assess potential exposure and lead the response.
• Prototype new approaches when existing tooling does not fit, run small experiments, and promote what works into platform standards.
• Write internal briefings on major developments and recommend when to adopt, pilot, or skip new tools or practices.
• Create and deliver AI security training across engineers, product teams, and the wider company, covering prompt injection, data leakage, excessive agency, and secure use of tools such as Claude, Glean, Devin, and Gemini.
• Act as the security voice in AI platform strategy by evaluating vendors and models, defining production readiness expectations, and contributing to AI governance across the AI lifecycle.
• Brief leadership on AI risk and investment priorities, and represent Realtor.com externally through conference talks, open-source work, or industry working groups.

Requirements

• 5+ years in cybersecurity, cloud security, AppSec/product security, or security platform engineering.
• Hands-on depth in AWS security and real experience in GCP (or strong multi-cloud background).
• Experience securing LLM or agentic systems, including prompt injection defenses, retrieval and data-boundary risks, agent identity, and model or tool supply-chain integrity.
• Threat modeling experience for products and platforms (not only infrastructure), with ability to lead sessions and translate outputs into requirements teams will follow.
• Hands-on experience building with agents, tool calling, or MCP, and with 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 operating within a larger security organization (parent company, central team, or federated model) while balancing local speed with enterprise alignment.
• Ability to follow AI security research, incident write-ups, and community work, and apply recent learnings to action.
• A builder’s mindset, including prototyping controls when playbooks do not yet exist.
• Ability to explain risk clearly to audiences ranging from PR comments to executive briefings to companywide training.

Technologies

• 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
• STRIDE, OWASP LLM/GenAI Top 10, MITRE ATLAS, OWASP ASVS, OWASP
• Terraform, CI/CD, GitHub Actions, SAST/SCA
• Python, TypeScript, Go, zero trust, least privilege, SSO/OIDC/OAuth, secrets management
• AI-BOM, 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

Work style

• Realtor.com balances creativity and innovation with in-person collaboration.
• For most roles, employees work four or more days in the office, enabling collaboration in person and strengthening culture.