Vulnerability Triage Security Evaluator

Human Union Data, Inc.
United States
15 days ago

Role details

Contract type
Permanent contract
Employment type
Part-time (≤ 32 hours)
Working hours
Regular working hours
Job source

Tech stack

Machine Learning Software Security Bug Reporting

Job description

  • Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Vulnerability Triage Security Evaluator assignments.
  • Document every successful attack with reproduction steps and the policy clause it violated.
  • Score model defenses across single-turn and multi-turn conversations.
  • Triage emerging attack vectors and route them to the safety team with severity ratings.
  • Maintain a personal library of attack patterns and propose new red-team rubrics.
  • Calibrate against the broader red-team cohort to keep coverage and severity consistent.

Requirements

  • Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Vulnerability Triage Security Evaluator work.
  • Strong written communication - your reports become the patch ticket.
  • Comfort working in policy-grey areas with clear documentation of what was attempted and why.
  • Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
  • Reliable async availability for at least 10 hours per week., * Background in offensive security, AppSec, or trust & safety operations.
  • Experience publishing or reproducing public adversarial-ML research.
  • Multilingual fluency for cross-language attack testing., * Adversarial prompting
  • Red-team analysis
  • Policy taxonomy
  • Failure documentation
  • Vulnerability Triage Security evaluation
  • Security review
  • Adversarial testing
  • Threat modeling
  • Vulnerability
  • Triage

Work model

Remote - US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

Benefits & conditions

  • Construct a 5-turn adversarial conversation that bypasses a specific policy clause and write up the patch ticket.
  • Score a model’s defenses against a known jailbreak pattern across 20 variants.
  • Propose a new red-team rubric category after spotting an emerging attack vector.
  • Reproduce a failure another reviewer reported and confirm the severity tag., Hourly rate confirmed after the interview process.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

5:19 min

Identifying vulnerabilities and automating Jira bug reports

Sergio Freire Sergio Freire · Europe 2026 Virtual

2:36 min

Applying supervised machine learning for practical rule extraction

Katja Träumner

1:30 min

The universal and shared team responsibility of software security

Julia Wilson Julia Wilson +1 · WWC 2025

1:29 min

Assisting security analysis using AI code review tools

Matteo Meucci Matteo Meucci · Europe 2026 Virtual

3:55 min

Establishing blameless dialogue surrounding critical software security vulnerabilities

Chris Heilmann +2 · LIVE

2:18 min

Streamlining feature requests and bug reports with templates

Dennis Doomen Dennis Doomen · WWC 2025

Videos

See all

Related articles

See all