Remote Frontier Model Misuse Red-Team Investigator
AuraOne
New York, NY
- Remote job
AuraOne is seeking a Frontier Model Misuse Risk Evaluator for a remote contractor role to stress-test AI systems against adversarial prompts. Reviewers craft attack scenarios, document failures with rigor, and pair each jailbreak with the violated policy clause to help patch gaps. You will design adversarial prompts, document reproduction steps, score defenses across turns, triage new attack vectors, and maintain a library of patterns while aligning with safety teams. #J-18808-Ljbffr AuraOne
Vacancy posted 5 days ago
Similar jobs that could be interesting for youBased on the Remote Frontier Model Misuse Red-Team Investigator in New York, NY vacancy
- ...Frontier Model Misuse 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...Remote jobHourly payFor contractors10 hours per week
- Frontier Model Misuse Risk Evaluator 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...Remote workHourly payFor contractors10 hours per week
$170k - $250k
Aisafety is hiring a Jailbreaking Lead (Red Team) in California. This role focuses on finding universal jailbreaks in leading AI models. The successful candidate will lead jailbreaking... ...offers the flexibility of a fully remote arrangement worldwide. #J-18808-Ljbffr AisafetyRemote jobWorldwide$125k - $190k
...Project Manager in Berkeley, California, to lead high-impact AI red-teaming initiatives. You will manage complex multi-party engagements,... ...engage with government and AI stakeholders. The role offers a remote global work possibility with a salary range of USD 125,000-190...Remote job- Location Remote Fluent Language Skills Required English... .... We are assembling a red team for this project -... ...data experts who probe AI models with adversarial inputs... ...jailbreaks, prompt injections, misuse cases, bias... ...AI red teaming at the frontier of safety Play a direct...Remote work
- .... Our advanced AI software and foundation models enable vehicles to perceive, understand, and... ...models for autonomy. Working at the frontier of a still-undefined field, you’ll collaborate with research and engineering teams to define what “good data” looks like for...Remote workFull timeWork at officeWork from homeVisa sponsorshipRelocation packageFlexible hours
GrabJobs
Fremont, CA4 days ago - Dormont Manufacturing Co in San Francisco, California is seeking a highly skilled specialist to own the red-teaming and adversarial evaluation pipeline for Reflection's models. The ideal candidate holds a graduate degree in Computer Science or a related field, has a strong...
- A leading AI research firm in New York, NY, is looking for a specialist to oversee the red-teaming and adversarial evaluation pipeline for their models. The ideal candidate should possess a graduate degree in Computer Science or a related field and have a deep understanding...
$23.13 - $39.45 per hour
...Location(s) Glendale, California, Remote-CA Details Kemper is one of the nation... ...and evolving needs. By joining our team, you are helping to provide an experience... ...delivers on our promises. The Special Investigator 1 will complete field and desk...Remote workWork at officeKemper
United States1 day ago- Trajectory Labs, PBC is building safety evals, red-teaming programs, and RL environments for frontier AI models. You will lead a growing red-team, own delivery for frontier lab customers, and automate workflows to scale impact. This player-coach role combines coding, strategy...Remote job
- ...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... ...reproducibility. This full-time W-2 position is remote within the United States, requiring about 35...Remote workFull time
- Location Glendale, California, Remote-CA Job Summary The Special Investigator 1 will complete field and desk assignments that support insurance claims referred... ...of digital/document metadata Able to work within a team environment as well as independently Experience using...Remote workWork at office
$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... ...securityThis position may be considered for a Remote or Hybrid (known internally at Target as "...Remote workFull timeTemporary workWork experience placementWork from homeFlexible hours$48 - $62 per hour
...identifying vulnerabilities, and producing actionable red-team data. This remote, text-based role focuses on testing AI... ...Responsibilities Test conversational AI models and agents for jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation...Remote workHourly paySaidGig
United States23 days ago$20 - $22 per hour
...clear, reproducible findings. This remote, hourly role focuses on text-based AI red teaming in both English and Punjabi. Role Overview You will test AI models and agents with adversarial inputs... ...jailbreaks, prompt injections, misuse cases, bias exploitation, and multi...Remote workHourly paySaidGig
United States9 days ago$91k - $169k
...Portfolio Analytics & Strategy Specialist (Fraud Model Analyst) within PNC's Technology organization,... ..., direction, and best practices to the modeling team. Can manage the work-sets of multiple model developers in remote locations, including offshore. Solves business...Remote workFull timeTemporary workPart timeWork experience placementWork at office$26 per hour
Type: Hourly contract Compensation: $26/hour Location: Remote Commitment: 10-40 hours/week Role Responsibilities Red-team conversational AI systems using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn adversarial strategies. Generate high...Remote jobHourly payContract work$48 - $62 per hour
...conversational AI systems for safety and misuse vulnerabilities in both English and... ...miss. Key Responsibilities Red team conversational AI models and agents, including jailbreaks, prompt... ...been exercised Work Terms Remote engagement Hourly employment All...Remote workHourly paySaidGig
United States23 days ago$20 - $22 per hour
...Type: Contract Compensation: $20–$22/hour Location: Remote Role Responsibilities Red team conversational AI models and agents, focusing on jailbreaks, prompt injections, misuse cases, and bias exploitation. Generate high-quality human data by...Remote workContract workSummer workMercor
New York, NY8 days ago- ...vulnerabilities, produce reproducible red-team data, and deliver actionable... ...harmful behaviors. This is a remote, text-based role focused on... ...Red team conversational AI models and agents by developing jailbreaks, prompt injections, misuse scenarios, bias exploitation techniques...Remote workHourly pay
SaidGig
United States23 days ago $43.89k - $69k
...Experienced Anti-Money Laundering (AML) Investigator , you will leverage your... ...Identify data anomalies and red flags related to money... ...internal and client quality control teams, make necessary adjustments... ...Degree required. Location is remote pending candidate permanent residence...Remote workOngoing contractPermanent employmentFull timeH1bWork at officeLocal areaWork from homeHome officeVisa sponsorshipMonday to Friday$145.9k - $234.2k
...infrastructure. This role reports to the Red Team Program Lead and works very deeply and closely... ...progressing toward a continuous red team model. Here’s What You’ll Need (Basic... ...license. #LI-CK1-SummaryLocation: Cambridge, Massachusetts; Remote - US; DigitalType: Full timeRemote workPermanent employmentFull timeWork at officeWork from home$29 - $45 per hour
...Type: Contract Compensation: $29–$45/hour Location: Remote Role Responsibilities Red team conversational AI models and agents by performing jailbreaks, prompt injections, misuse cases, and bias exploitation. Generate high-quality human data by...Remote workContract workSummer workMercor
New York, NY11 days ago- About the Team Preparedness is a critical Safety Research... ...evolving capabilities of frontier AI systems. Mitigation. Keeping misuse safeguards, alignment... ...boundaries of our frontier models. Specifically, we are looking... ...box and have a robust “red-teaming mindset” Have...Permanent employmentTemporary work
- ABOUT THE TEAM Models are becoming increasingly capable—moving from tools... ...real world. Mitigating the frontier risks resulting from these... ...systems. Mitigation. Keeping misuse and misalignment safeguards,... ...Evaluate and design effective red‑teaming pipelines to examine...
$100k - $169k
...Valley; Quincy; Rancho Cordova; Red Bluff; Redding; Richmond;... ...through incident reporting and investigations, overseeing Electric... ...Electric Compliance Assurance Team as an Incident Investigator.... ...is hybrid, working from your remote office and assigned office based...Remote workFull timeWork experience placementWork at officeFlexible hours$295k
About the team The Safety Systems org ensures that OpenAI's most capable models can be responsibly developed and deployed... ...Framework. Frontier AI models have the potential... ..., and internal red teaming, and mitigations... ...to reduce severe cyber misuse across OpenAI's products...- ...seeking a Researcher for Frontier Cybersecurity Risks to... ...reduces severe cyber misuse across OpenAI’s products... ...product, and engineering teams to ensure protections... ...effective. You will design model-enabled safeguards... ..., and lead testing and red-teaming efforts to adapt...
$60 - $90 per hour
...Machine Learning Engineer — Model Evaluation & Experimentation... ...–$90/hour Location: Remote Commitment: 35 hours/... ...Evaluate models to identify where frontier models fall short. Collaborate... ...@mercor.com PS: Our team reviews applications daily. Please...Remote workFull timeContract workSummer workMercor
Remote17 hours ago- ...build cutting-edge foundation AI models and end-to-end products that... ....We’re training and deploying frontier models for enterprises who are... ...our customers. Cohere is a team of researchers, engineers, designers... ...to other offices if you are remote, plus an annual company...Remote workFull timeWork at officeLocal areaHome office
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Remote Frontier Model Misuse Red-Team Investigator. Be the first to apply!
Related searches
- clinical investigator New York, NY
- compliance investigator New York, NY
- defense investigator New York, NY
- opm background investigator New York, NY
- background investigator New York, NY
- healthcare investigator New York, NY
- corporate investigator New York, NY
- surveillance investigator New York, NY
- ethics investigator New York, NY
- legal investigator New York, NY