AI Architect

{
  "content_hash": "7c8c1cf70b0b744d51feedc6b47cc794d324f035621bf3e4ab80ba8cd9c8ff5f",
  "source_hash": "98be1ace3208b0f2f0cc14de02170d875be6f40398967a1c9aa8a49aaaa8577c",
  "last_changed_at": "2026-06-03T10:34:09.815Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Dublin, Dublin, d1, Ireland",
    "city": "Dublin",
    "region": "Dublin",
    "country": null,
    "is_remote": false,
    "confidence": 0.8
  },
  "salary_max": null,
  "salary_min": null,
  "inferred_at": "2026-06-06T10:25:54.982Z",
  "launch_scope": {
    "reason": "bamboohr_production_catalog",
    "included": true,
    "location": {
      "raw": "Dublin, Dublin, d1, Ireland",
      "city": "Dublin",
      "region": "Dublin",
      "country": null,
      "is_remote": false,
      "confidence": 0.8
    },
    "countries": []
  },
  "remote_policy": null,
  "salary_period": null,
  "workplace_type": null,
  "salary_currency": null
}

{}

{
  "list_job": {
    "id": "285",
    "isRemote": null,
    "location": {
      "city": "Dublin",
      "state": "Dublin"
    },
    "atsLocation": {
      "city": null,
      "state": null,
      "country": null,
      "province": null
    },
    "departmentId": null,
    "locationType": "2",
    "jobOpeningName": "AI Architect ",
    "departmentLabel": null,
    "employmentStatusLabel": "Full-Time"
  },
  "detail_errors": [],
  "detail_job_opening": {
    "location": {
      "city": "Dublin",
      "state": "Dublin",
      "postalCode": "d1",
      "addressCountry": "Ireland"
    },
    "datePosted": "2026-06-02",
    "atsLocation": {
      "city": null,
      "state": null,
      "country": null,
      "countryId": null
    },
    "description": "<p><span style=\"font-weight: bold\">AI ARCHITECT - Role Overview</span></p>\n<p>We are seeking an experienced AI Architect to lead the design, development, and production deployment of autonomous multi-agent systems. You will move beyond simple chatbots to build stateful, goal-oriented agentic workflows that can reliably execute complex business logic.</p>\n<p><br></p>\n<p><span style=\"font-weight: bold\">Key Responsibilities</span></p>\n<p><br></p>\n<p><span style=\"font-size: 12pt; font-weight: bold\">Architecture &amp; System Design</span></p>\n<ul>\n<li><span style=\"font-weight: bold\">Design multi-agent architectures</span> (e.g., Supervisor-Worker, Hierarchical Teams) capable of breaking down complex user queries into sub-tasks.</li>\n<li>Define the <span style=\"font-weight: bold\">state management strategy</span> to ensure agents retain context, memory, and user intent across long-running workflows.</li>\n<li>Architect robust <span style=\"font-weight: bold\">Retrieval-Augmented Generation (RAG)</span> pipelines that allow agents to query proprietary data with high precision.</li>\n<li>Select and integrate appropriate <span style=\"font-weight: bold\">LLM orchestration frameworks</span> (e.g., LangGraph, AutoGen, CrewAI) based on use-case requirements.</li>\n<li>\n</li></ul>\n<p><span style=\"font-weight: bold\">Engineering &amp; Development</span></p>\n<ul>\n<li>Implement <span style=\"font-weight: bold\">tool-use capabilities</span> (function calling), enabling agents to interact with internal APIs, databases, and third-party SaaS platforms safely.</li>\n<li>Develop <span style=\"font-weight: bold\">guardrails and steering mechanisms</span> (e.g., NeMo Guardrails, LMQL) to ensure agents stay \"on-rails\" and avoid hallucinations or unsafe actions.</li>\n<li>Optimize <span style=\"font-weight: bold\">prompt engineering strategies</span> (Chain-of-Thought, ReAct, Tree of Thoughts) for maximum reliability and minimum latency.</li>\n<li>Oversee the transition from prototype to production, ensuring code is modular, testable, and scalable.</li>\n</ul>\n<p><br></p>\n<p><span style=\"font-weight: bold\">Production Operations (LLMOps)</span></p>\n<ul>\n<li>Implement <span style=\"font-weight: bold\">evaluation frameworks</span> (e.g., Ragas, TruLens, DeepEval) to quantitatively measure agent performance, accuracy, and hallucination rates before deployment.</li>\n<li>Design <span style=\"font-weight: bold\">observability dashboards</span> (using tools like LangSmith, Arize, or Datadog) to trace agent reasoning steps, token usage, and latency in real-time.</li>\n<li>Manage <span style=\"font-weight: bold\">cost and performance trade-offs</span>, implementing caching strategies and selecting the right model mix (e.g., routing simpler tasks to smaller/cheaper models like GPT-4o-mini or Llama 3).</li>\n</ul>\n<p><br></p>\n<p><span style=\"font-weight: bold\">Technical Qualifications</span></p>\n<p><br></p>\n<p><span style=\"font-weight: bold\">Core Tech Stack</span></p>\n<ul>\n<li><span style=\"font-weight: bold\">Languages:</span> Expert proficiency in <span style=\"font-weight: bold\">Python</span>; familiarity with TypeScript is a plus.</li>\n<li><span style=\"font-weight: bold\">LLM Frameworks:</span> Deep experience with <span style=\"font-weight: bold\">LangChain</span> and specifically agentic libraries like <span style=\"font-weight: bold\">LangGraph</span>, <span style=\"font-weight: bold\">AutoGen</span>, or <span style=\"font-weight: bold\">Semantic Kernel</span>.</li>\n<li><span style=\"font-weight: bold\">Vector Databases:</span> Experience deploying and managing vector stores like <span style=\"font-weight: bold\">Pinecone, Weaviate, Qdrant,</span> or <span style=\"font-weight: bold\">pgvector</span>.</li>\n<li><span style=\"font-weight: bold\">Model APIs:</span> Hands-on experience integrating <span style=\"font-weight: bold\">OpenAI (GPT-4), Anthropic (Claude),</span> and open-source models (via <span style=\"font-weight: bold\">Ollama</span> or <span style=\"font-weight: bold\">vLLM</span>).</li>\n</ul>\n<p><br></p>\n<p><span style=\"font-weight: bold\">Infrastructure &amp; DevOps</span></p>\n<ul>\n<li>Experience containerizing AI applications (<span style=\"font-weight: bold\">Docker, Kubernetes</span>) for cloud deployment (AWS/Azure/GCP).</li>\n<li>Familiarity with <span style=\"font-weight: bold\">serverless architectures</span> for handling asynchronous agent tasks.</li>\n<li>Knowledge of <span style=\"font-weight: bold\">API security standards</span> (OAuth, API Keys) for securing agent tool access.</li>\n</ul>\n<p><br></p>\n<p><span style=\"font-weight: bold\">Nice-to-Haves (The \"Edge\")</span></p>\n<ul>\n<li>Experience <span style=\"font-weight: bold\">fine-tuning</span> small language models (SLMs) for specific domain tasks to reduce costs and improve latency.</li>\n<li>Background in <span style=\"font-weight: bold\">Graph RAG</span> (using Knowledge Graphs alongside Vector DBs) for better reasoning capabilities.</li>\n<li>Experience dealing with <span style=\"font-weight: bold\">structured outputs</span> (using Pydantic/Instructor) to force LLMs to return valid JSON/Schematic data.</li>\n</ul>\n<p> </p>",
    "compensation": null,
    "departmentId": null,
    "locationType": "2",
    "seekPromoted": false,
    "jobCategoryId": null,
    "jobOpeningName": "AI Architect ",
    "departmentLabel": "",
    "jobOpeningStatus": "Open",
    "minimumExperience": "Senior Manager/Supervisor",
    "jobOpeningShareUrl": "https://xerxesglobal.bamboohr.com/careers/285",
    "employmentStatusLabel": "Full-Time"
  }
}