{"id":186854,"url":"https://alion.io/job/replit-ai-agent-security-architect","title":"AI Agent Security Architect","company":{"id":2425,"name":"Replit","domain":"replit.com","url":"https://alion.io/company/replit","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":89,"open_postings":33,"ghost_share":0,"stale_share":0.242,"repost_share":0,"time_to_fill_p50_days":84,"computed_at":"2026-10-22T06:10:10Z"}},"role":"Security","role_family":"Security","seniority":"staff","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Foster City, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":217000,"max_usd":431000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":414},"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AutoGen","optional":false},{"name":"CrewAI","optional":false},{"name":"Docker","optional":false},{"name":"EU AI Act","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"ISO 42001","optional":false},{"name":"JavaScript","optional":false},{"name":"LangChain","optional":false},{"name":"Least Privilege","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"NIST AI RMF","optional":false},{"name":"OWASP Top 10","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Red Teaming","optional":false},{"name":"Replit","optional":false},{"name":"Threat Modeling","optional":false},{"name":"TypeScript","optional":false},{"name":"WebAssembly","optional":false}],"status":"live","first_seen_at":"2026-09-01T04:28:54Z","employer_posted_date":"2026-09-01","last_verified_at":"2026-10-23T04:02:26Z","board_verified":true,"closed_at":null,"days_open":51,"trust":{"level":"ok","repost_count":0,"flags":[],"days_open":51},"description":"Replit is the agentic software creation platform that enables anyone to build applications using natural language. With millions of users worldwide, Replit is democratizing software development by removing traditional barriers to application creation.\nAbout the Role\nWe are looking for an AI Agent Security Architect to function as the primary technical authority for Replit’s autonomous and AI agent security blueprint. In this critical role, you will design, implement, and maintain the runtime defense systems, guardrail frameworks, and sandboxing architectures that govern AI agents executing code, invoking tools, and reasoning across our platform. You will be a key technical contributor-leading high-impact AI security initiatives and bridging the gap between non-deterministic AI behavior and rigorous cybersecurity controls for both engineering and executive leadership.\nWhat You'll Do\nAI Agent Security Strategy & Technical Execution\n\nAI Agent Security Blueprint: Define the long-term vision and architectural patterns for securing autonomous agent workflows, Model Context Protocol (MCP) integrations, multi-turn reasoning loops, and multi-agent coordination.\n\nRuntime Guardrails & Policy Enforcement: Architect and deploy dynamic input/output guardrail systems, semantic firewalls, and real-time intent verification filters to prevent goal hijacking, system prompt leaks, and indirect prompt injections.\n\nAgent Execution & Tool Sandboxing: Partner with Infrastructure and AppSec teams to design secure, short-lived, micro-isolated environments (e.g., microVMs, WebAssembly, container sandboxes) where agents can dynamically execute code, run shell commands, and interact with host operating systems safely.\n\nAgentic Threat Modeling & Red Teaming: Conduct specialized threat modeling against non-deterministic systems. Lead automated and manual AI red-teaming initiatives to uncover vulnerabilities in RAG context pipelines, vector stores, and tool-calling interfaces.\n\nIdentity, Delegation & Least Privilege: Architect fine-grained permission models and step-up Human-in-the-Loop (HITL) authorization patterns for agents acting on behalf of users-ensuring agents never exceed the delegated privileges of the end user or misuse API keys.\n\nContext & Memory Boundary Security: Design strict data isolation and poisoning prevention controls for vector databases, retrieval-augmented generation (RAG) pipelines, and long-term conversation memories across multi-tenant workloads.\n\nRisk Management & Cross-Functional Enablement\n\nMaintain the AI Security Source of Truth: Define, document, and maintain authoritative secure design patterns and SDKs for engineering teams building internal or customer-facing AI agent capabilities.\n\nContribution to Risk Register: Identify, quantify, and document non-deterministic and agentic security risks (e.g., OWASP Top 10 for LLMs & AI Agents, MITRE ATLAS), ensuring they are accurately represented in the Cybersecurity Risk Register.\n\nAuditability & Observability: Design tamper-evident logging and telemetry standards for agent reasoning chains, tool execution history, and context assembly to support incident response, forensics, and GRC requirements.\n\nCompliance & Sales Enablement: Partner with GRC to translate complex AI security controls into enterprise-ready audit documentation (e.g., ISO 42001, NIST AI RMF, EU AI Act readiness) and support Sales on complex enterprise security inquiries regarding AI safety.\n\nRequired Skills & Experience\n6+ years of experience in security engineering or security architecture, with at least 2+ years dedicated specifically to AI/ML security, LLM application security, or securing agentic frameworks.\n\nDeep understanding of agentic architectures and protocols (e.g., Model Context. Protocol (MCP), LangChain, AutoGen, CrewAI, ReAct frameworks, and vector database technologies).\n\nHands-on expertise with threat vectors unique to agentic AI: Indirect Prompt\n\nInjection, Goal Hijacking, Tool Parameter Tampering, Data Poisoning, and Context Contamination.\n\nStrong background in applying safety standards and risk frameworks such as OWASP Top 10 for LLMs & AI Agents, NIST AI RMF, and MITRE ATLAS.\n\nProficiency in Python, Go, or TypeScript/JavaScript with a proven track record of reviewing code and building functional security tooling or guardrails.\n\nExperience authoring, maintaining, and evangelizing technical security architecture documentation.\n\nExceptional ability to communicate complex non-deterministic AI risks to both deep technical engineers and executive stakeholders.\n\nProven track record of contributing to an enterprise Cybersecurity Risk Register.\n\nBonus Qualifications\nExperience designing runtime sandboxing and isolation technologies (e.g., Firecracker, gVisor, Docker, WebAssembly) for dynamic code execution environments.\n\nFull-Time Employee Benefits Include:\nCompetitive Salary & Equity\n401(k) Program with a 4% match (US Only)\nHealth, Dental, Vision and Life Insurance\nShort Term and Long Term Disability\nPaid Parental, Medical, Caregiver Leave\nFlexible Time Off (FTO) + Holidays\nCommuter Benefits (In-Office & US Only)\nMonthly Wellness Stipend\nAutonomous Work Environment\nIn Office Set-Up Reimbursement (In-Office Only)\nQuarterly Team Gatherings\nIn Office Amenities (In-Office Only)\nWant to learn more about what we are up to?\nSelf-driving Company\n\nReplit Agent at Scale\n\nAI Adoption\n\nBuild Open-Source Apps\n\nInterviewing + Culture at Replit\nOperating Principles\n\nReasons not to work at Replit\n\nTo achieve our mission of making programming more accessible around the world, we need our team to be representative of the world. We welcome your unique perspective and experiences in shaping this product. We encourage people from all kinds of backgrounds to apply, including and especially candidates from underrepresented and non-traditional backgrounds.","description_format":"text","description_chars":5865,"description_truncated":false,"requirements":{"experience_years_min":6,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity","Flexible time off","Life insurance"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Penetration Testing","Code Intelligence","AI Development Tools","Website Builders"],"lifecycle":[{"event":"open","at":"2026-09-01T19:33:20Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 29 · green card filings: 1","filings_12m":29,"filings_prev_12m":5,"green_card_filings_12m":1,"median_offered_wage_usd":201833,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":2}],"liveness":{"score":78,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.867,"p_room":0.9,"age_days":51,"expected_fill_days":84,"reasons":["conf:1","velocity","win:mid"],"computed_at":"2026-10-22T06:10:10Z"},"pay":null,"html_url":"https://alion.io/job/replit-ai-agent-security-architect","json_url":"https://alion.io/job/replit-ai-agent-security-architect.json","meta":{"generated_at":"2026-10-23T04:26:32Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":7251,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-24T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":2425},"rest":"https://alion.io/mcp/rest/get_company?id=2425"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Freplit-ai-agent-security-architect"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Freplit-ai-agent-security-architect"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Freplit-ai-agent-security-architect"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/replit-ai-agent-security-architect\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Freplit-ai-agent-security-architect"}]}