AI Engineer, Executive Communication Agents

Location: Irvine, CA (5 days onsite) Type: Fixed Term About FieldAI FieldAI is building advanced AI systems to power real-world autonomy. As a fast-growing company at the forefront of innovation, we move quickly and operate with high standards, supporting leaders who are shaping the future of AI. Role Overview We're hiring an experienced AI engineer to design, build, and own the Executive Communication Agents that power our leadership and communications operations. You'll work directly with our C-level leadership and their EAs to automate and augment high-stakes workflows, including scheduling, inbox management, meeting prep and follow-ups, task prioritization, travel, project coordination, internal comms, and executive research, and to set the technical direction for how FieldAI uses its own technology internally. This role combines deep AI engineering with strong product and communications sensibilities. The agents you build will collaborate closely with executives, suggest scheduling decisions, and support leadership in day-to-day operations. You'll prototype on Monday, ship to real users by Friday, and iterate based on what you see them actually doing with it. Compensation and Benefits Our salary range is highly competitive with the market, but we take into consideration an individual's background and experience in determining final salary; base pay offered may vary considerably depending on geographic location, job-related knowledge, skills, and experience. Why Join Field AI? We are solving one of the world’s most complex challenges: deploying robots in unstructured, previously unknown environments. Our Field Foundational Models™ set a new standard in perception, planning, localization, and manipulation, ensuring our approach is explainable and safe for deployment. You will have the opportunity to work with a world-class team that thrives on creativity, resilience, and bold thinking. With a decade-long track record of deploying solutions in the field, winning DARPA challenge segments, and bringing expertise from organizations like DeepMind, NASA JPL, Boston Dynamics, NVIDIA, Amazon, Tesla Autopilot, Cruise Self-Driving, Zoox, Toyota Research Institute, and SpaceX, we are set to achieve our ambitious goals. Be Part of the Next Robotics Revolution To tackle such ambitious challenges, we need a team as unique as our vision — innovators who go beyond conventional methods and are eager to tackle tough, uncharted questions. We’re seeking individuals who challenge the status quo, dive into uncharted territory, and bring interdisciplinary expertise. Our team requires not only top AI talent but also exceptional software developers, engineers, product designers, field deployment experts, and communicators. We are headquartered in always-sunny Irvine, Southern California and have US based and global teammates. Join us, shape the future, and be part of a fun, close-knit team on an exciting journey! We celebrate diversity and are committed to creating an inclusive environment for all employees. Candidates and employees are always evaluated based on merit, qualifications, and performance. We will never discriminate on the basis of race, color, gender, national origin, ethnicity, veteran status, disability status, age, sexual orientation, gender identity, marital status, mental or physical disability, or any other legally protected status. What You’ll Get To Do Architect and build production-grade Executive Communication Agents for workflows including scheduling, email triage and drafting, meeting prep and follow-ups, travel coordination, project coordination and action item tracking, and briefing generation Own the full agent stack: orchestration, memory, tool use, evals, guardrails, and the integrations that connect agents to Google Workspace, Slack, calendar, and travel systems, and internal knowledge sources Partner directly with C-level leadership and EAs as your first users to observe their workflows, identify the highest-leverage automation opportunities, and translate messy real-world processes into shipped systems Set the bar for agent quality by building evaluation frameworks, defining reliability and safety standards, and ensuring agents are trustworthy Move fast across the full stack when needed: backend services, agent orchestration, Chrome extensions, and Slack bots, whatever gets the workflow unblocked Influence product direction for internal AI tooling and help translate learnings into patterns the broader company can build on What You Have 3+ years of software engineering experience, with 2+ years building LLM-powered products or agents in production Strong proficiency in Python and/or TypeScript and experience with modern agent frameworks (LangGraph, CrewAI, custom orchestration, etc.) Deep hands-on work with LLM APIs, RAG, tool use, function calling, prompt engineering, and eval design Experience shipping products that integrate with Google Workspace, Slack, or similar enterprise APIs A track record of shipping end-to-end, including side projects, internal tools, or production features you took from idea to live users quickly Excellent written and verbal communication, with the ability to work directly with executives, write clearly, and care about the quality of the text your agents produce Strong product instincts and comfort operating in ambiguous, fast-moving environments High judgment and discretion when working with confidential executive information Ability to work onsite in Irvine, CA, five days per week The Extras That Set You Apart Prior experience building AI assistants, copilots, or agentic products used by non-technical end users Background in a high-growth startup or early-stage AI company Experience working directly with executives and EA teams Contributions to open-source agent frameworks or applied AI tooling Experience with multi-agent systems, long-horizon planning, or human-in-the-loop workflows

{
  "content_hash": "4b8dc646ced8c47f5a1a8e91c1e03c999aa43703e170155147c3cd73ecf4861a",
  "source_hash": "71c011c13b2a1b70be53a3b94d4695702ff3d92f5ebbfaaec2ae6d20cde58ae3",
  "last_changed_at": "2026-05-29T06:56:56.179Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Irvine, CA",
    "city": "Irvine",
    "region": "CA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": null,
  "salary_min": null,
  "inferred_at": "2026-06-06T18:40:25.946Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Irvine, CA",
      "city": "Irvine",
      "region": "CA",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.9
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": null,
  "workplace_type": "on_site",
  "salary_currency": null
}

{}

{
  "lists": [
    {
      "text": "What You’ll Get To Do",
      "content": "\n<li>Architect and build production-grade Executive Communication Agents for workflows including scheduling, email triage and drafting, meeting prep and follow-ups, travel coordination, project coordination and action item tracking, and briefing generation</li>\n<li>Own the full agent stack: orchestration, memory, tool use, evals, guardrails, and the integrations that connect agents to Google Workspace, Slack, calendar, and travel systems, and internal knowledge sources</li>\n<li>Partner directly with C-level leadership and EAs as your first users to observe their workflows, identify the highest-leverage automation opportunities, and translate messy real-world processes into shipped systems</li>\n<li>Set the bar for agent quality by building evaluation frameworks, defining reliability and safety standards, and ensuring agents are trustworthy</li>\n<li>Move fast across the full stack when needed: backend services, agent orchestration, Chrome extensions, and Slack bots, whatever gets the workflow unblocked</li>\n<li>Influence product direction for internal AI tooling and help translate learnings into patterns the broader company can build on</li>\n"
    },
    {
      "text": "What You Have",
      "content": "\n<li>3+ years of software engineering experience, with 2+ years building LLM-powered products or agents in production</li>\n<li>Strong proficiency in Python and/or TypeScript and experience with modern agent frameworks (LangGraph, CrewAI, custom orchestration, etc.)</li>\n<li>Deep hands-on work with LLM APIs, RAG, tool use, function calling, prompt engineering, and eval design</li>\n<li>Experience shipping products that integrate with Google Workspace, Slack, or similar enterprise APIs</li>\n<li>A track record of shipping end-to-end, including side projects, internal tools, or production features you took from idea to live users quickly</li>\n<li>Excellent written and verbal communication, with the ability to work directly with executives, write clearly, and care about the quality of the text your agents produce</li>\n<li>Strong product instincts and comfort operating in ambiguous, fast-moving environments</li>\n<li>High judgment and discretion when working with confidential executive information</li>\n<li>Ability to work onsite in Irvine, CA, five days per week</li>\n"
    },
    {
      "text": "The Extras That Set You Apart",
      "content": "<div>\n\n<li>Prior experience building AI assistants, copilots, or agentic products used by non-technical end users</li>\n<li>Background in a high-growth startup or early-stage AI company</li>\n<li>Experience working directly with executives and EA teams</li>\n<li>Contributions to open-source agent frameworks or applied AI tooling</li>\n<li>Experience with multi-agent systems, long-horizon planning, or human-in-the-loop workflows</li>\n\n</div>"
    }
  ],
  "country": "US",
  "createdAt": 1777399262989,
  "updatedAt": null,
  "categories": {
    "team": "Applied AI",
    "location": "Irvine, CA",
    "commitment": "Fixed-Term",
    "department": "Communications",
    "allLocations": [
      "Irvine, CA"
    ]
  },
  "salaryRange": null,
  "workplaceType": "onsite"
}