{"schemaVersion":"jobsearcher.job.v1","id":"8f5b027806dbb732a3dc4e59","url":"https://jobsearcher.com/jobs/8f5b027806dbb732a3dc4e59","canonicalUrl":"https://jobsearcher.com/jobs/8f5b027806dbb732a3dc4e59","title":"Game Engineer","description":"Own the AI safety layer for Realtor.com's RealAssist, an LLM-powered real-estate assistant used across web and mobile. On the AI Integrations Team at News Corp, you will build and tune LLM safety guardrails that act as a launch gate for Fair Housing compliance and content moderation, with runtime prompt-injection and jailbreak screening designed for production.What you'll doBuild, tune, and take end-to-end ownership of LLM-as-a-judge classifiers for Fair-Housing compliance and content moderation, targeting high recall on disallowed content without overblocking legitimate usersDesign and run guardrail evaluation pipelines, including labeled dataset curation, train/test/validate splits, and offline prod-replay to evaluate overblockingUse defensible metrics by reporting confusion matrices and precision/recall/F1 per category to guide safety decisionsIntegrate and operate cloud guardrail services as a runtime prompt-injection/jailbreak screening layer, including fail-open behavior and alertingRed-team the assistant and wire safety regression checks into CI to prevent silent guardrail degradation as the product growsManage guardrail infrastructure as code using Terraform (templates, IAM, and project shape), and participate in technical design reviews and architecture discussionsPartner with ML, backend, product, and legal/compliance stakeholders to define risk tiering and get new AI capabilities through safety review before launchIndependently design, implement, and tune guardrail and evaluation systems with a focus on balancing safety, latency, and user experience; write clean, maintainable, well-tested codeKeep eval datasets calibrated to real traffic and emerging attack patterns, staying current with AI-safety research and new guardrail toolingWhat you bringAI Safety & Evaluation Expertise (required)4+ years of professional software/ML engineering experience with hands-on LLM application workBachelor's degree or equivalent experienceStrong Python proficiencyReal classification-metrics literacy: precision/recall/F1 (macro vs weighted), confusion matrix debugging, dataset curation, and calibration to production distributionExperience evaluating LLM prompts/classifiers with an eval framework such as DeepEval, RAGAS, Arize Phoenix, LangSmith, OpenAI Evals, or a homegrown harnessAbility to turn small seed sets into robust labeled eval datasets using dataset-synthesis and prompt-optimization loopsFamiliarity with prompt-injection/jailbreak defense concepts, including OWASP LLM Top 10, input/output filtering, least-privilege tool access, and adversarial testingHands-on experience with cloud guardrail services: Google Cloud Model ArmorAWS Bedrock Guardrails, or Azure AI Content SafetyTerraform/IaC for cloud infrastructureExperience with Google Cloud Vertex AI / GeminiUnderstanding of monitoring and observability tools (for example, New Relic or similar)Exposure to regulated, compliance-sensitive domains (fair housing, fair lending, healthcare, finance, trust & safety)Red-teaming or AI-security backgroundTools you'll work withPythonDeepEvalRAGASArize PhoenixLangSmithOpenAI EvalsOWASP LLM Top 10Google Cloud Model ArmorAWS Bedrock GuardrailsAzure AI Content SafetyTerraformGoogle Cloud Vertex AI / GeminiNew RelicOnsite role with strong support and collaborationThe AI Integrations Team is a cross-functional squad building how Realtor.com integrates AI across its products. The work blends creativity and innovation with in-person collaboration. For most roles, employees work four or more days in officeBenefitsInclusive and competitive medical, Rx, dental, and vision coverageFamily forming benefits13 Paid HolidaysFlexible Time Off8 hours of paid volunteer time offImmediate eligibility into the Company 401(k) plan with 3.5% company matchTuition Reimbursement for degreed and non-degreed programs1:1 personalized Financial Planning SessionsFree snacks and refreshments in each office locationStudent Debt Retirement Savings Match programJ-18808-Ljbffr","company":"Datajobscom","rawCompany":"datajobscom","city":"Austin","state":"TX","isRemote":false,"isActive":false,"createdAt":"2026-10-20T15:58:12.377Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1299.05","title":"Information Security Engineers","slug":"information-security-engineers"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Game Engineer","description":"Own the AI safety layer for Realtor.com's RealAssist, an LLM-powered real-estate assistant used across web and mobile. On the AI Integrations Team at News Corp, you will build and tune LLM safety guardrails that act as a launch gate for Fair Housing compliance and content moderation, with runtime prompt-injection and jailbreak screening designed for production.What you'll doBuild, tune, and take end-to-end ownership of LLM-as-a-judge classifiers for Fair-Housing compliance and content moderation, targeting high recall on disallowed content without overblocking legitimate usersDesign and run guardrail evaluation pipelines, including labeled dataset curation, train/test/validate splits, and offline prod-replay to evaluate overblockingUse defensible metrics by reporting confusion matrices and precision/recall/F1 per category to guide safety decisionsIntegrate and operate cloud guardrail services as a runtime prompt-injection/jailbreak screening layer, including fail-open behavior and alertingRed-team the assistant and wire safety regression checks into CI to prevent silent guardrail degradation as the product growsManage guardrail infrastructure as code using Terraform (templates, IAM, and project shape), and participate in technical design reviews and architecture discussionsPartner with ML, backend, product, and legal/compliance stakeholders to define risk tiering and get new AI capabilities through safety review before launchIndependently design, implement, and tune guardrail and evaluation systems with a focus on balancing safety, latency, and user experience; write clean, maintainable, well-tested codeKeep eval datasets calibrated to real traffic and emerging attack patterns, staying current with AI-safety research and new guardrail toolingWhat you bringAI Safety & Evaluation Expertise (required)4+ years of professional software/ML engineering experience with hands-on LLM application workBachelor's degree or equivalent experienceStrong Python proficiencyReal classification-metrics literacy: precision/recall/F1 (macro vs weighted), confusion matrix debugging, dataset curation, and calibration to production distributionExperience evaluating LLM prompts/classifiers with an eval framework such as DeepEval, RAGAS, Arize Phoenix, LangSmith, OpenAI Evals, or a homegrown harnessAbility to turn small seed sets into robust labeled eval datasets using dataset-synthesis and prompt-optimization loopsFamiliarity with prompt-injection/jailbreak defense concepts, including OWASP LLM Top 10, input/output filtering, least-privilege tool access, and adversarial testingHands-on experience with cloud guardrail services: Google Cloud Model ArmorAWS Bedrock Guardrails, or Azure AI Content SafetyTerraform/IaC for cloud infrastructureExperience with Google Cloud Vertex AI / GeminiUnderstanding of monitoring and observability tools (for example, New Relic or similar)Exposure to regulated, compliance-sensitive domains (fair housing, fair lending, healthcare, finance, trust & safety)Red-teaming or AI-security backgroundTools you'll work withPythonDeepEvalRAGASArize PhoenixLangSmithOpenAI EvalsOWASP LLM Top 10Google Cloud Model ArmorAWS Bedrock GuardrailsAzure AI Content SafetyTerraformGoogle Cloud Vertex AI / GeminiNew RelicOnsite role with strong support and collaborationThe AI Integrations Team is a cross-functional squad building how Realtor.com integrates AI across its products. The work blends creativity and innovation with in-person collaboration. For most roles, employees work four or more days in officeBenefitsInclusive and competitive medical, Rx, dental, and vision coverageFamily forming benefits13 Paid HolidaysFlexible Time Off8 hours of paid volunteer time offImmediate eligibility into the Company 401(k) plan with 3.5% company matchTuition Reimbursement for degreed and non-degreed programs1:1 personalized Financial Planning SessionsFree snacks and refreshments in each office locationStudent Debt Retirement Savings Match programJ-18808-Ljbffr","datePosted":"2026-10-20T15:58:12.377Z","dateModified":"2026-10-20T15:58:12.377Z","hiringOrganization":{"@type":"Organization","name":"Datajobscom","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Austin","addressRegion":"TX","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"8f5b027806dbb732a3dc4e59"},"url":"https://jobsearcher.com/jobs/8f5b027806dbb732a3dc4e59"}}