Manipulation Risk Red Team Specialist
AuraOne Human Data
Manipulation Risk Red Team Specialist is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.
Why this role matters
Adversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them.
Responsibilities
- Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Manipulation Risk Red Team Specialist 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.
Qualifications
- Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Manipulation Risk Red Team Specialist 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.
Example tasks
- 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.
Nice to have
- Background in offensive security, AppSec, or trust & safety operations.
- Experience publishing or reproducing public adversarial-ML research.
- Multilingual fluency for cross-language attack testing.
Skills
- Adversarial prompting
- Red-team analysis
- Policy taxonomy
- Failure documentation
- Manipulation Risk Red Team evaluation
- AI safety
- Red-team evaluation
- Policy rubrics
- Manipulation
- Risk
Work model
Remote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.
Compensation
Hourly rate confirmed after the interview process.
Application process
Apply through AuraOne's specialist intake for role-specific routing and review. Final project scope, schedule, and contractor terms are confirmed before placement.
Vacancy posted a month ago
Similar jobs that could be interesting for youBased on the Manipulation Risk Red Team Specialist in Remote vacancy
$157k - $227k
...testing on a global scale.Partner with the Alphabet’s Enterprise Red Team cross-functional working group in collaboration with digital... ...and strategy.Minimum qualifications:Bachelor’s degree in Security Risk Management, or equivalent practical experience.10 years of experience...Risk- ...been attacked — by us. We are assembling a red team for this project - human data experts... ...misuse cases, bias exploitation, multi-turn manipulation Generate high-quality human data:... ...classify vulnerabilities, and flag systemic risks Apply structure: follow taxonomies,...RiskRemote work
Mercor Inc
New York, NY1 day ago $121.9k - $197.1k
...What You'll Do The Adversarial Red Team Associate Principal is responsible for strengthening OCC's security posture by conducting covert... ...remediated findings with IT owners. Perform threat modeling, security risk assessments, and independent reviews of OCC's security, network,...RiskWork at officeRemote work2 days per weekThe Options Clearing Corporation
Springfield, IL2 days ago$61.64k - $69.74k
...Academy our mission is to empower at-risk youth to improve their educational levels... ...of Youth Academy Residential Specialist 2 (Cadre Team Member) where you will work in a diverse... ...does include identifying and managing manipulative behaviors. Demonstrate mature judgment...RiskPermanent employmentFull timePart timeImmediate startRemote workFlexible hoursShift workState of Washington
Olympia, WA5 days ago$48 - $62 per hour
...This remote role focuses on text-based AI red teaming in both English and Danish. Key... ...cases, bias exploitation, and multi-turn manipulation. Review AI outputs involving sensitive... ...classify vulnerabilities, flag systemic risks, and create high-quality human data....RiskHourly payRemote workSaidGig
United Statesa month ago$17 - $25 per hour
...safety data, and help identify risks before they reach production.... ...exploitation, and multi-turn manipulation. Annotate model failures, classify... ..., and attack cases that teams can use to improve AI systems.... ...required. Prior experience in AI red teaming, adversarial AI work,...RiskHourly payRemote workSaidGig
United Statesa month ago- ...This text-based role focuses on finding risks that automated testing may miss and turning... ...attack cases. Key Responsibilities Red team conversational AI models and agents... ...cases, bias exploitation, and multi-turn manipulation. Review AI outputs involving sensitive...RiskHourly payRemote work
SaidGig
United Statesa month ago $28.74 per hour
...Location: Remote Role Responsibilities Red team conversational AI models and agents (... ...misuse cases, bias exploitation, multi-turn manipulation). Generate high-quality human data by... ...vulnerabilities, and flagging systemic risks. Apply structured taxonomies, benchmarks...RiskRemote jobHourly payFull timeContract workPart time- Mercor is seeking a research-focused professional to join a GenAI red-team within a leading AI lab network. The role involves probing frontier models, designing robust evaluation tasks, and documenting findings for reproducibility. This full-time W-2 position is remote...Full timeRemote work
- Mercor is building a remote red team for AI safety. You will lead adversarial testing of conversational AI models, focusing on jailbreaks, prompt injections, misuse, and bias exploitation. You will generate high-quality human data, annotate failures, classify vulnerabilities...Remote job
- As a Banking Specialist Team Lead, you help create the energy and excitement around Amerant Bank products, providing the right solutions and... ..., monitor and make any recommendation deemed necessary to the Risk Management Committee in order to assess, reduce, eliminate or...RiskWork experience placementBank staffNight shift
$141 - $180 per hour
...day. A member of our recruitment team will provide more details.The Vice President, Global Red Team & AI Security Operations... ...translating findings into measurable risk reduction in partnership with... ...prompt injection, model manipulation, jailbreak resistance, retrieval...RiskFull timeWork at officeLocal areaRemote work1 day per week- Cincinnatus LLC is building capabilities to stress-test frontier AI models. You will work in a red-teaming setup to design and probe multi-step tasks that reveal vulnerabilities, edge cases, and failure modes in cutting-edge AI systems, with approximately 35 hours per week...Remote jobFull time
- Mercor is seeking a remote Red Team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate actionable... ...will annotate failures, classify vulnerabilities, and document risks using established taxonomies and playbooks. The role offers...RiskRemote job
$23 - $26 per hour
...Job Description Job Description Job Title: ACT Team Family Specialist Department: Behavioral Services Reports to: Director of ACT Team... ...Identify strengths and weaknesses, needs and goals. Identify risk factors regarding harm to self and/or others. Provide crisis...RiskWork from homeOswego Health
Fulton, NY18 days ago- Mercor is building a remote AI safety red team to probe conversational models and surface vulnerabilities in high-sensitivity topics. You will annotate failures, classify risks, and generate reproducible reports for customers to act on. Before exposure to content, topics...RiskRemote job
- ...updates as new positions become available. Substance Use Specialist Home Base ACT I Team $2500 retention bonus This position is eligible for $2500... ...assessments and provide appropriate crisis interventionsand risk management as needed. Teach consumers adult daily living skills...RiskFull timeWork from homeMonday to Friday
- Mercor seeks a remote AI red-teaming specialist fluent in English and Portuguese to assess safety of conversational models. You will simulate jailbreaks... ..., follow taxonomies and playbooks, and clearly communicate risks to technical and non-technical stakeholders. Prior red-...RiskRemote job
$132k - $238k
...Target cares about and invests in you as a team member, so that you can take care of... ...TARGET CYBERSECURITY AS A LEAD ENGINEER - RED TEAMAbout UsWorking at Target means helping... ...adversary behavior to communicate discovered risk effectively, and benefit from continuous development...RiskFull timeTemporary workWork experience placementRemote workWork from homeFlexible hours$50 - $90 per hour
...generation AI systems with practical offensive-security expertise. As a Red Team Lead, you will turn real-world cybersecurity knowledge into... ...and improve red-team benchmarks to reflect evolving security risks and leading practices. Produce clear methodologies and...RiskHourly payContract workRemote workSaidGig
United Statesmore than 2 months ago$26 per hour
...Location: Remote Commitment: 10-40 hours/week Role Responsibilities Red-team conversational AI systems using jailbreaks, prompt injections,... ...failures, classifying vulnerabilities, and flagging systemic risks. Follow structured taxonomies, benchmarks, and testing...RiskRemote jobHourly payContract work$29.43 - $45.39 per hour
...The Cardiac/Pulmonary Rehab Specialist plays a vital role in helping... ...that promote recovery, reduce risk factors, and enhance overall... ...part of a multidisciplinary team, the specialist provides education... ...of hands and fingers to manipulate complex and delicate equipment...RiskHourly payFull timeImmediate startRemote workIntermountain Health
Brighton, CO7 hours ago- Select how often (in days) to receive an alert: The Team Relations Specialist (TRS) serves as a trusted advisor and strategic partner to leaders... ...team member relations issues, mitigate organizational risk, and ensure consistent application of company policies, procedures...RiskMinimum wageTemporary workLocal area
- Role Description The Cybersecurity Red Team Analyst - Principal will plan and direct efforts in developing and testing tools, tactics,... ...validating viability of threats for more effective prioritization of risks. The principal role will also assist the Red Team manager in...RiskFull timeRemote workFlexible hours
Huntington National Bank
Remote9 days ago $20 - $22 per hour
...role focused on producing reproducible red team data and actionable reports that help customers... ..., bias exploitation, and multi-turn manipulation Generate high-quality human data by... ...vulnerabilities, and flagging systemic risks Apply structure by following taxonomies...RiskHourly payRemote workSaidGig
United States4 days ago$48 - $62 per hour
...improves model safety. This is a text-based red teaming role focused on discovering jailbreaks,... ..., bias exploitation, and multi-turn manipulation. Review AI outputs that touch on... ...vulnerabilities, and flagging systemic risks. Follow established taxonomies, benchmarks...RiskHourly payRemote workSaidGig
United States5 days ago$20 - $22 per hour
...Role Overview You will join a red team of human experts who probe conversational AI to... ...cases, bias exploitation, and multi-turn manipulation Review AI outputs that touch on sensitive... ...vulnerabilities, and flagging systemic risks Apply structure by following...RiskHourly payRemote workSaidGig
United States4 days ago$17 - $25 per hour
...adversarial inputs, surface systematic risks, and produce human-quality data customers... ...text-based. Key Responsibilities Red team conversational AI models and agents, including... ..., bias exploitation, and multi-turn manipulation Generate high-quality human data by...RiskHourly payRemote workSaidGig
United States5 days ago$17 - $25 per hour
...Role Overview Join a red team of human data experts who probe conversational AI models... ...cases, bias exploitation, and multi-turn manipulation Generate high-quality human data by annotating... ...vulnerabilities, and flagging systemic risks Apply structure and consistency by...RiskHourly payRemote workSaidGig
United States4 days ago$48 - $62 per hour
...Role Overview Work as a human red team specialist probing conversational AI to find vulnerabilities... ..., bias exploitation, and multi-turn manipulation. Create high-quality human data by... ..., and flagging systemic risks. Follow taxonomies, benchmarks, and...RiskHourly payRemote workSaidGig
United States6 days ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Manipulation Risk Red Team Specialist. Be the first to apply!
