> Markdown version of [/jobs/ext/4701724-principal-architect-autonomous-agent-safety-control-systems](https://www.wearedevelopers.com/jobs/ext/4701724-principal-architect-autonomous-agent-safety-control-systems). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Principal Architect - Autonomous Agent Safety & Control Systems - **Company:** Verizon Communications Inc. - **Location:** Ashburn, VA, United States (Remote available) - **Experience:** Experienced - **Salary:** $120,500 - $231,000 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Cloud Computing, Cloud Engineering, Continuous Integration, DevOps, Identity and Access Management, Python (Programming Language), Network Control, Software Product Management, Gemini Enterprise (Agent Platform), Zero Trust Network Access, DataOps, Google Cloud, Retrieval-Augmented Generation, Large Language Models, Multi-Agent Systems, Model Validation, Langfuse — LLM Observability and Analytics Platform, Agentic-AI, AI Platforms, Kubernetes, Information Technology, Deployment Automation, Hardware Infrastructure, Restful APIs, Model Context Protocol, Api Management, Agent2Agent Protocol - **Published:** November 13, 2026 - **Apply:** https://jobs.localjobnetwork.com/apply/add/88750563/1 ## About the Role You've moved beyond standard RAG prototypes and API wrappers to solve the hard, unglamorous systems challenges of autonomous enterprise AI. You should be equally comfortable designing multi-agent execution frameworks and building the deterministic safety layers, zero-trust controls, and sub-second circuit breakers that prevent autonomous systems from going rogue in production., * Bachelor's degree or four or more years of work experience. * Six or more years of relevant experience required, demonstrated through one or a combination of work and/or military experience, or specialized training. * Four or more years of experience as an AI Engineer and Architect designing and deploying scalable, multi-agent frameworks leveraging emerging interaction standards such as Model Context Protocol (MCP) and Agent-to-Agent (A2A communications * Experience in LLM operationalization, orchestration frameworks, model evaluation frameworks, agentic workflows, and automated safety testing. * Experience in cloud architecture (AWS Bedrock) * Experience with AI Security, Zero Trust, and Model Governance * Experience defending agentic ecosystems against prompt injection, data exfiltration, tool abuse, hallucinations, and guarantees factual accuracy * Experience shipping software into high-traffic, regulated, or enterprise production environments where downtime, inaccurate data, or out-of-bounds agent actions carry severe real-world consequences. Even better if you also have one or more of the following... * Masters or PhD in Computer Science, AI/ML, or related field. * Six or more years of platform engineering, as well as applied ML engineering, or AI science * Advanced skills in programming in Python, Kubernetes * Advanced knowledge of CI/CD deployment tools * Knowledge of automated safety testing and Agentic Identity & Access Management * Experience building real-time telemetry, trace-level monitoring (OpenTelemetry, Langfuse, Arize), and automated fail-safes. When an agent experiences semantic drift, enters a recursive tool-calling loop, or attempts an unauthorized action without human oversight, your systems isolate the process and revert state in milliseconds. ## Description You'll combine your advanced AI engineering skills with responsible AI, integrity, and legal (RIL) to unleash the power and promise of enterprise AI through the use of autonomous agents. With tens of millions of connected devices, petabytes of streaming network telemetry, and strategic partnerships like Google Cloud's Agentic Data Cloud and Gemini Enterprise, Nvidia for edge AI and GPU infrastructure, AWS, and as the only telecom company to participate in Anthropic's Glasswing project, you won't just run experiments in a sandbox- you'll be at the center of every AI project Verizon is building. What you'll be doing... The Enterprise AI Control Plane team is adding a hands-on architectural engineer to build the complex system connecting Verizon's AI developer platforms (AWS Bedrock, Atlas AI) with our governance hubs (Engram, Agent Registry). This role provides a dedicated builder who architects robust APIs, automated CI/CD guardrails, and real-time observability telemetry to ensure autonomous agents run safely at enterprise scale. In this role you will... * Architect and code automated CI/CD governance pipelines that inject Security and RIL (Responsible AI, Integrity, Legal) guardrails directly into the deployment lifecycle. * Implement advanced agent simulation and continuous real-time observability telemetry for production LLMs. * Interact daily with AI Platform Engineers, DevOps/DataOps teams, Data Scientists, and AI product developers across various Business Units to integrate their models into the governance framework * Architect Identity & Access Management (IAM) and routing logic within the Agent Gateway to ensure autonomous workflows operate with secure access boundaries. * Build robust API integrations connecting developer platforms (Vegas, Atlas AI) seamlessly with Verizon governance hubs (Engram, Agent Registry)., Where you'll be workingIn this hybrid role, you'll have a defined work location that includes working from home and a minimum of three days per week in the office, which will be set by your manager. Employees are responsible for maintaining compliance with hybrid work policies.