Red Teaming Expert

{
  "content_hash": "0b84b4e91bd95783f352f29e3dbfd60713b0ac198cbd51af77990acc5497635b",
  "source_hash": "4bd6e15f43b088dee20262dc65c8e85b206a1c1b8c1f09a48969cdd05978bbec",
  "last_changed_at": "2026-05-30T06:04:22.595Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Seattle, Washington, United States",
    "city": "Seattle",
    "region": "WA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.8
  },
  "salary_max": null,
  "salary_min": 30,
  "inferred_at": "2026-06-06T09:39:29.915Z",
  "launch_scope": {
    "reason": "bamboohr_production_catalog",
    "included": true,
    "location": {
      "raw": "Seattle, Washington, United States",
      "city": "Seattle",
      "region": "WA",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.8
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": "hour",
  "workplace_type": null,
  "salary_currency": "USD"
}

{}

{
  "list_job": {
    "id": "74",
    "isRemote": null,
    "location": {
      "city": null,
      "state": null
    },
    "atsLocation": {
      "city": "Seattle",
      "state": "Washington",
      "country": "United States",
      "province": null
    },
    "departmentId": "18634",
    "locationType": "1",
    "jobOpeningName": "Red Teaming Expert",
    "departmentLabel": "Experts",
    "employmentStatusLabel": "Contractor"
  },
  "detail_errors": [],
  "detail_job_opening": {
    "location": {
      "city": null,
      "state": null,
      "postalCode": null,
      "addressCountry": null
    },
    "datePosted": "2026-04-29",
    "atsLocation": {
      "city": "Seattle",
      "state": "Washington",
      "country": "United States",
      "countryId": "1"
    },
    "description": "<ul></ul>\n<p><span style=\"font-family: Inter, sans-serif; font-size: 12pt; font-weight: bold\">About mpathic.ai</span></p>\n<p><span style=\"font-size: 10pt\">Keeping the human in AI. mpathic is a trusted leader in advancing quality and safety in AI systems through expert-led evaluation and human data. We partner with leading technology companies to support red teaming, trust &amp; safety, expert annotation, and model evaluation across high-stakes domains.</span></p>\n<p><br></p>\n<p><span style=\"font-family: Inter, sans-serif; font-size: 12pt; font-weight: bold\">About the Role</span></p>\n<p><span style=\"font-size: 10pt\">mpathic is seeking <span style=\"font-weight: bold\">part-time, project-based Red Teaming Experts</span> to support a red-teaming and evaluation campaign focused on AI safety and model behavior in sensitive, real-world interactions.</span></p>\n<p><br><br></p>\n<p><span style=\"font-size: 10pt\">In this role, you will design, simulate, and evaluate conversations with AI systems to assess safety, risk, and behavioral performance. You will identify failure modes, edge cases, and policy gaps—particularly in scenarios involving distress, ambiguity, or escalation.</span><br></p>\n<p><br><br></p>\n<p><span style=\"font-family: Arial, sans-serif; font-size: 10pt\"><span style=\"font-weight: bold\">This role involves roleplaying and reviewing clinical scenarios with AI agents. </span>As such, we are ideally seeking candidates who bring <span style=\"font-weight: bold\">creative or performance-driven strengths</span>, as these competencies enhance the realism, nuance, and emotional depth needed for AI safety testing. Examples of these can include, but are not limited to: </span></p>\n<ul>\n<li><span style=\"font-family: Arial, sans-serif; font-size: 10pt\">Theatre degrees or studies</span></li>\n<li><span style=\"font-family: Arial, sans-serif; font-size: 10pt\">Acting, theatre, improv, or voice-over experience </span></li>\n</ul>\n<ul>\n<li><span style=\"font-family: Arial, sans-serif; font-size: 10pt\">Strong writing skills, especially dialogue or scenario writing </span></li>\n</ul>\n<ul>\n<li><span style=\"font-family: Arial, sans-serif; font-size: 10pt\">Experience creating or inhabiting characters (e.g., performers, TTRPG roleplay, narrative designers) </span></li>\n</ul>\n<ul>\n<li><span style=\"font-family: Arial, sans-serif; font-size: 10pt\">Conversational design, interaction writing, or scripted roleplay experience </span></li>\n</ul>\n<ul>\n<li><span style=\"font-family: Arial, sans-serif; font-size: 10pt\">Participation in gaming, interactive storytelling, or digital communities where roleplay is common </span></li>\n</ul>\n<p><br></p>\n<p><span style=\"font-family: Inter, sans-serif; font-size: 10pt\"><span style=\"font-family: Inter, sans-serif; font-size: 12pt; font-weight: bold\">What You’ll Be Working On </span></span></p>\n<p><span style=\"font-size: 10pt\">You will help identify, prevent, and characterize risks that emerge when users interact with AI systems.</span></p>\n<p><br><br></p>\n<p><span style=\"font-size: 10pt\">Responsibilities may include:</span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">Designing and executing red-teaming scenarios across diverse user behaviors</span></li>\n<li><span style=\"font-size: 10pt\">Reviewing AI-generated responses for safety, accuracy, and policy compliance</span></li>\n<li><span style=\"font-size: 10pt\">Identifying failure modes, edge cases, and behavioral risks</span></li>\n<li><span style=\"font-size: 10pt\">Assessing whether AI appropriately recognizes and responds to distress or escalation</span></li>\n<li><span style=\"font-size: 10pt\">Evaluating tone, boundaries, and appropriateness in sensitive interactions</span></li>\n<li><span style=\"font-size: 10pt\">Detecting misleading, overconfident, or unsafe responses</span></li>\n<li><span style=\"font-size: 10pt\">Evaluating multi-turn conversations for consistency and risk handling</span></li>\n<li><span style=\"font-size: 10pt\">Identifying gaps in responses, including missed signals or incomplete handling</span></li>\n<li><span style=\"font-size: 10pt\">Conducting qualitative analysis to identify behavioral patterns and system weaknesses</span></li>\n<li><span style=\"font-size: 10pt\">Documenting edge cases, failure patterns, and safety risks</span></li>\n<li><span style=\"font-size: 10pt\">Applying or contributing to evaluation rubrics, taxonomies, and frameworks</span></li>\n<li><span style=\"font-size: 10pt\">Supporting quality assurance (QA) to ensure consistency across evaluations</span></li>\n<li><span style=\"font-size: 10pt\">Collaborating with internal teams on AI safety and evaluation improvements</span></li>\n<li><span style=\"font-size: 10pt\">Participating in red teaming exercises to surface system vulnerabilities</span></li>\n<li><span style=\"font-size: 10pt\">Maintaining strict confidentiality and quality standards</span></li>\n</ul>\n<p><br></p>\n<p><span style=\"font-weight: bold\">What We’re Looking For</span></p>\n<p><span style=\"font-size: 10pt\">Successful candidates are detail-oriented, analytically strong, and experienced in evaluating or stress-testing AI systems in complex or high-risk scenarios.</span></p>\n<p><br><br></p>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Professional experience in one or more of the following:</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">LLM red teaming or AI safety evaluation</span></li>\n<li><span style=\"font-size: 10pt\">Trust &amp; safety, content moderation, or policy enforcement</span></li>\n<li><span style=\"font-size: 10pt\">AI/ML evaluation, annotation, or QA workflows</span></li>\n<li><span style=\"font-size: 10pt\">Conversational analysis or behavioral risk assessment</span></li>\n<li><span style=\"font-size: 10pt\">Work involving sensitive or high-stakes user interactions</span></li>\n</ul>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Strong understanding of:</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">AI safety principles and common failure modes</span></li>\n<li><span style=\"font-size: 10pt\">Behavioral risk, escalation patterns, and edge-case handling</span></li>\n<li><span style=\"font-size: 10pt\">Mental health sensitivity, boundaries, and responsible AI behavior</span></li>\n<li><span style=\"font-size: 10pt\">How users express distress, confusion, or harmful intent in conversation</span></li>\n</ul>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Ability to identify:</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">Safety violations and policy gaps</span></li>\n<li><span style=\"font-size: 10pt\">Missed or mishandled risk signals</span></li>\n<li><span style=\"font-size: 10pt\">Unsafe, misleading, or overconfident responses</span></li>\n<li><span style=\"font-size: 10pt\">Inappropriate tone or boundary-setting</span></li>\n<li><span style=\"font-size: 10pt\">Failures in escalation, de-escalation, or resolution</span></li>\n<li><span style=\"font-size: 10pt\">Inconsistencies across multi-turn interactions</span></li>\n</ul>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Experience with or Interest in:</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">Red teaming methodologies and adversarial testing</span></li>\n<li><span style=\"font-size: 10pt\">Evaluating conversational AI systems or chatbots</span></li>\n<li><span style=\"font-size: 10pt\">Developing or applying evaluation frameworks and rubrics</span></li>\n<li><span style=\"font-size: 10pt\">Understanding how AI systems perform under real user behavior</span></li>\n</ul>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Comfort with:</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">Tech tools and platforms (Slack, spreadsheets, dashboards)</span></li>\n<li><span style=\"font-size: 10pt\">Evaluating AI-generated responses (no coding required, but must be tech-comfortable)</span></li>\n<li><span style=\"font-size: 10pt\">Ambiguity, iteration, and feedback-driven workflows</span></li>\n</ul>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Willingness to:</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">Sign NDAs and work with sensitive or high-impact content</span></li>\n</ul>\n<p><span style=\"font-size: 10pt\"><span style=\"font-weight: bold\">Nice to Have (Not Required)</span></span></p>\n<ul>\n<li><span style=\"font-size: 10pt\">Background in mental health, behavioral science, or psychology</span></li>\n<li><span style=\"font-size: 10pt\">Experience in QA, annotation, or qualitative analysis</span></li>\n<li><span style=\"font-size: 10pt\">Experience with AI systems in sensitive domains (e.g., healthcare, safety)</span></li>\n<li><span style=\"font-size: 10pt\">Familiarity with evaluation metrics or safety frameworks</span></li>\n</ul>\n<p><br></p>\n<p><span style=\"font-size: 10pt; font-weight: bold\">Compensation</span></p>\n<p><span style=\"font-size: 10pt\">$30-60/hour, depending on experience and specific project tasks/difficulty</span></p>",
    "compensation": "$30–$40/hour depending on project difficulty",
    "departmentId": "18634",
    "locationType": "1",
    "seekPromoted": false,
    "jobCategoryId": null,
    "jobOpeningName": "Red Teaming Expert",
    "departmentLabel": "Experts",
    "jobOpeningStatus": "Open",
    "minimumExperience": "Mid-level",
    "jobOpeningShareUrl": "https://mpathic2.bamboohr.com/careers/74",
    "employmentStatusLabel": "Contractor"
  }
}