bluedoor data·Job Postings API·bluedoor.sh ↗

HomeCompaniesCareers Silveredgegs Icims ComLLM Security Evaluation Expert

LLM Security Evaluation Expert

Careers Silveredgegs Icims Com · Columbia, MD, US · Active · iCIMS

Job facts

FieldValue
CompanyCareers Silveredgegs Icims Com
TitleLLM Security Evaluation Expert
Normalized title-
Department / teamInformation Technology
LocationColumbia, MD, United States
Work model-
Employment typeFull Time
Salary-
Statusactive
ATS provideriCIMS
Posted / first seen2026-04-14 / 2026-05-31
Changed / last seen2026-06-01 / 2026-06-06

Related slices

PageWhat it containsOpen
Company jobsActive postings from Careers Silveredgegs Icims Com.Open
Company breakdownsRole, location, ATS, and work model facets for this company.Open
ATS provider jobsActive postings observed through iCIMS.Open
Provider filtered searchThe same provider as a filtered job collection.Open
City jobsActive postings in Columbia.Open
Department jobsActive postings in Information Technology.Open
Lifecycle eventsOpen, update, close, and reopen events for this posting.Open
Original postingCanonical source or apply URL captured from the ATS.Open

Linked records

CompanyCareers Silveredgegs Icims Com
Source54dae19b-8199-4a7e-8936-d9536e5583db
ATS provideriCIMS

Description

Overview SilverEdge Government Solutions is seeking a highly skilled LLM Security Evaluation Expert to join our team. In this role, you will be responsible for rigorously testing the security and integrity of Large Language Models (LLMs). Your primary focus will be on designing and executing sophisticated adversarial prompt attacks to identify potential vulnerabilities, assess the model's resistance to exploitation, and ensure it maintains consistent, secure behavior. This is a critical role in safeguarding our AI systems and ensuring they operate responsibly. Required Qualifications TS/SCI with Polygraph level Clearance Strong knowledge of how LLMs work, including their architecture, training processes, capabilities, and inherent limitations. Familiarity with prominent LLM families (e.g., GPT series, Claude, Llama, PaLM) and their common characteristics. Proven experience in crafting and refining prompts to elicit specific behaviors or bypass restrictions in LLMs. Demonstrable understanding of techniques like jailbreaking, prompt injection, role-playing attacks, and exploiting model biases. Strong understanding of cybersecurity principles and common attack vectors, particularly as they apply to AI/ML systems. Ability to think like an attacker and anticipate potential exploits. Excellent ability to analyze complex systems, identify subtle vulnerabilities, and systematically test hypotheses. Clear and concise written and verbal communication skills, with the ability to document technical findings thoroughly. Understanding of the ethical implications of AI security and commitment to responsible testing practices. About SilverEdge SilverEdge Government Solutions was founded on the belief that nurturing talent and collaborating closely with our customers enables us to think big and deliver the best for our country. Our mission is to bring top technology talent together to solve the world’s most challenging problems while protecting the United States and our allies.SilverEdge Government Solutions, LLC is an Equal Opportunity Employer and applicants receive lawful consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.

Full job record

Job IDa856c3b01f63d7e5c69b9a0b8f9faa398ff4e381
Org ID041b2d25-bb35-454a-bbb2-927618e26e74
Source ID54dae19b-8199-4a7e-8936-d9536e5583db
Board ID54dae19b-8199-4a7e-8936-d9536e5583db
Providericims
Provider Job Key2727
TitleLLM Security Evaluation Expert
Normalized Title
Statusactive
Activeyes
Location TextColumbia, MD, US
DepartmentInformation Technology
Team
Employment Typefull_time
Workplace Type
Remote Policy
CountryUnited States
RegionMD
CityColumbia
Salary RawOverview SilverEdge Government Solutions is seeking a highly skilled LLM Security Evaluation Expert to join our team. In this role, you will be responsible for rigorously testing the security and integrity of Large Language Models (LLMs). Your primary focus will be on designing and executing sophisticated adversarial prompt attacks to identify potential vulnerabilities, assess the model's resistance to exploitation, and ensure it maintains consistent, secure behavior. This is a critical role in safeguarding our AI systems and ensuring they operate responsibly. Required Qualifications TS/SCI with Polygraph level Clearance Strong knowledge of how LLMs work, including their architecture, training processes, capabilities, and inherent limitations. Familiarity with prominent LLM families (e.g., GPT series, Claude, Llama, PaLM) and their common characteristics. Proven experience in crafting and refining prompts to elicit specific behaviors or bypass restrictions in LLMs. Demonstrable understanding of techniques like jailbreaking, prompt injection, role-playing attacks, and exploiting model biases. Strong understanding of cybersecurity principles and common attack vectors, particularly as they apply to AI/ML systems. Ability to think like an attacker and anticipate potential exploits. Excellent ability to analyze complex systems, identify subtle vulnerabilities, and systematically test hypotheses. Clear and concise written and verbal communication skills, with the ability to document technical findings thoroughly. Understanding of the ethical implications of AI security and commitment to responsible testing practices. About SilverEdge SilverEdge Government Solutions was founded on the belief that nurturing talent and collaborating closely with our customers enables us to think big and deliver the best for our country. Our mission is to bring top technology talent together to solve the world’s most challenging problems while protecting the United States and our allies.SilverEdge Government Solutions, LLC is an Equal Opportunity Employer and applicants receive lawful consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.
Salary Min
Salary Max
Salary Currency
Salary Period
Source URLhttps://careers-silveredgegs.icims.com/jobs/2727/llm-security-evaluation-expert/job
Apply URLhttps://careers-silveredgegs.icims.com/jobs/2727/llm-security-evaluation-expert/job
First Seen At2026-05-31 18:40:48Z
Last Seen At2026-06-06 20:21:01Z
Last Checked At2026-06-06 20:21:01Z
Last Changed At2026-06-01 13:50:02Z
Inactive At
Source Posted At2026-04-14 04:00:00Z
Source Updated At2026-01-22 15:39:51Z
Raw Payload Uris3://job-postings-prod-raw-590183727216/raw/provider=icims/board=careers-silveredgegs.icims.com/date=2026-06-06/2026-06-06T20-21-00-799Z-22a21940bffb43a8e24b282319577d2b33ed7fdd03103fdf10f96cb7f2265f87.json
Event Fields
{
  "content_hash": "f00bc96c2d518425bcfd48ff95f89d09bfafe97a428ebf38f63b188d8852da7c",
  "source_hash": "07eff82485af40f19283e5280cc50631975d339c46a96fc021f5a24e6a3acc76",
  "last_changed_at": "2026-06-01T13:50:02.431Z",
  "active_status": "active"
}
Parsed Structured
{
  "language": "en",
  "location": {
    "raw": "Columbia, MD, US",
    "city": "Columbia",
    "region": "MD",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.8
  },
  "salary_max": null,
  "salary_min": null,
  "inferred_at": "2026-06-06T20:21:01.243Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "Columbia, MD, US",
      "city": "Columbia",
      "region": "MD",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.8
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": null,
  "workplace_type": null,
  "salary_currency": null
}
Extensions
{}
Native Structured
{
  "json_ld": {
    "url": "https://careers-silveredgegs.icims.com/jobs/2727/llm-security-evaluation-expert/job",
    "@type": "JobPosting",
    "title": "LLM Security Evaluation Expert",
    "@context": "http://schema.org",
    "datePosted": "2026-04-14T04:00:00.000Z",
    "description": "<h2>Overview</h2>\n<p>SilverEdge Government Solutions is seeking a highly skilled LLM Security Evaluation Expert to join our team. In this role, you will be responsible for rigorously testing the security and integrity of Large Language Models (LLMs). Your primary focus will be on designing and executing sophisticated adversarial prompt attacks to identify potential vulnerabilities, assess the model's resistance to exploitation, and ensure it maintains consistent, secure behavior. This is a critical role in safeguarding our AI systems and ensuring they operate responsibly.</p>\n<h2>Required Qualifications</h2>\n<ul>\n <li>TS/SCI with Polygraph level Clearance</li>\n <li>Strong knowledge of how LLMs work, including their architecture, training processes, capabilities, and inherent limitations.</li>\n <li>Familiarity with prominent LLM families (e.g., GPT series, Claude, Llama, PaLM) and their common characteristics.</li>\n <li>Proven experience in crafting and refining prompts to elicit specific behaviors or bypass restrictions in LLMs.</li>\n <li>Demonstrable understanding of techniques like jailbreaking, prompt injection, role-playing attacks, and exploiting model biases.</li>\n <li>Strong understanding of cybersecurity principles and common attack vectors, particularly as they apply to AI/ML systems.</li>\n <li>Ability to think like an attacker and anticipate potential exploits.</li>\n <li>Excellent ability to analyze complex systems, identify subtle vulnerabilities, and systematically test hypotheses.</li>\n <li>Clear and concise written and verbal communication skills, with the ability to document technical findings thoroughly.</li>\n <li>Understanding of the ethical implications of AI security and commitment to responsible testing practices.</li>\n</ul>\n<h2>About SilverEdge</h2>\n<p>SilverEdge Government Solutions was founded on the belief that nurturing talent and collaborating closely with our customers enables us to think big and deliver the best for our country. Our mission is to bring top technology talent together to solve the world’s most challenging problems while protecting the United States and our allies.SilverEdge Government Solutions, LLC is an Equal Opportunity Employer and applicants receive lawful consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.</p>",
    "directApply": true,
    "jobLocation": [
      {
        "@type": "Place",
        "address": {
          "@type": "PostalAddress",
          "postalCode": "UNAVAILABLE",
          "addressRegion": "MD",
          "streetAddress": "UNAVAILABLE",
          "addressCountry": "US",
          "addressLocality": "Columbia",
          "postOfficeBoxNumber": "UNAVAILABLE"
        }
      }
    ],
    "validThrough": "2027-04-14T04:00:00.000Z",
    "employmentType": "FULL_TIME",
    "qualifications": "TS/SCI w/ Poly",
    "hiringOrganization": {
      "name": "SilverEdge",
      "@type": "Organization",
      "sameAs": "www.silveredge-gs.com"
    },
    "occupationalCategory": "Information Technology"
  },
  "detail_meta": {
    "url": "https://careers-silveredgegs.icims.com/jobs/2727/llm-security-evaluation-expert/job?in_iframe=1",
    "http_status": 200,
    "content_type": "text/html;charset=UTF-8",
    "response_bytes": 31730,
    "compact_response_bytes": 3391,
    "original_response_bytes": 31730
  },
  "sitemap_job": {
    "id": "2727",
    "url": "https://careers-silveredgegs.icims.com/jobs/2727/llm-security-evaluation-expert/job",
    "slug": "llm-security-evaluation-expert",
    "lastmod": "2026-01-22T10:39:51-05:00"
  },
  "detail_errors": []
}
Get this page with API

Rendered from the bluedoor Job Postings API. Reproduce it:

GET https://api.bluedoor.sh/job-postings/v1/jobs/a856c3b01f63d7e5c69b9a0b8f9faa398ff4e381?include=descriptionJSON
GET https://api.bluedoor.sh/job-postings/v1/orgs/041b2d25-bb35-454a-bbb2-927618e26e74JSON
GET https://api.bluedoor.sh/job-postings/v1/sources/54dae19b-8199-4a7e-8936-d9536e5583dbJSON
GET https://api.bluedoor.sh/job-postings/v1/jobs/a856c3b01f63d7e5c69b9a0b8f9faa398ff4e381/eventsJSON