Remote AI Safety Red-Team Evaluator (Adversarial Prompts)
AuraOne
New York, NY
- Remote job
As part of AuraOne's safety-focused team, you will design 5‑turn attack scenarios, reproduce reported failures, and help harden AI systems before broader deployment. This is a contract position with US-eligibility suitable for remote workers. #J-18808-Ljbffr AuraOne
Vacancy posted 2 days ago
Similar jobs that could be interesting for youBased on the Remote AI Safety Red-Team Evaluator (Adversarial Prompts) in New York, NY vacancy
- AuraOne is seeking a remote contractor to perform Chemical Safety Risk Evaluation by designing adversarial prompts, documenting failures with reproduction steps, and scoring... ...week. Applicants should have experience in red-teaming AI systems, familiarity with jailbreaking...Remote jobFor contractors10 hours per week
- ...AI Safety and Red-Team 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 jobHourly payFor contractors10 hours per week
$26 per hour
...6/hour Location: Remote Commitment: 10-40... ...Responsibilities Red-team conversational AI systems using jailbreaks, prompt injections, misuse... ..., and multi-turn adversarial strategies.... ...adversarial test cases. Evaluate AI outputs across... ...with defined safety guidelines. Requirements...Remote jobHourly payContract work- AuraOne is seeking a Prompt Injection Security Evaluator for a remote contractor role. You will design adversarial prompts, document failures with reproducible steps, and score... ...pattern libraries, and coordinating with the safety team to ensure consistent coverage and #J-188...Remote jobFor contractors
$26 per hour
A tech consulting firm is seeking a remote contractor to engage in AI red teaming activities. The ideal candidate will work on evaluating conversational AI systems and generating human... ..., along with prior experience in adversarial AI testing or cybersecurity. This is a...Remote jobHourly payFor contractors10 hours per weekFlexible hours- YO IT Consulting is hiring a Red-Teaming Quality Assurance Lead to oversee quality and consistency across AI safety evaluation projects. This remote role demands strong expertise in AI... ...teams and ensuring the quality of adversarial prompts and AI-generated outputs. Your...Remote job
- AuraOne seeks a remote contractor to assess Robot Policy Compliance failures in AI systems. You will craft 5-turn adversarial prompts, document failures with exact reproduction steps, and... ...regression testing. Ideal candidates bring red-team experience, strong written...Remote jobFor contractors10 hours per week
- ...AI Red Team Engineer We're looking for an AI Red Team... .... You'll own hands-on adversarial testing end to end: find... ...White Circle is an AI Safety company building the... ...Test for jailbreaks, prompt injection, system-prompt... ..., and LLM-as-judge evaluation. Familiarity with OWASP...Remote workLocal area
White Circle
United States3 days ago - Location Remote Fluent Language Skills... ...the safest AI is the one that... ...are assembling a red team for this project... ...AI models with adversarial inputs, surface... ...agents: jailbreaks, prompt injections,... ...AI systems Evaluation coverage expands... ...customers trust the safety of their AI...Remote work
- ...progressive technology company is seeking a remote AI Red Teamer to assess conversational AI... ...and identify vulnerabilities through red teaming exercises. Candidates should be fluent... ...with a background in cybersecurity or adversarial testing. This role involves producing actionable...Remote workHourly pay
Crossing Hurdles
New York, NY2 days ago - ...Humana Inc. is seeking a technical Lead for our red team to run objective-based adversary emulation campaigns across network, social... ...tradecraft, and engagement rules, and advance AI-augmented red teaming. This is a remote role within Humana's offensive security...Remote work
Humana Inc
Carson City, NV1 day ago - Mercor is building a fully remote red team to probe AI models for safety, resilience, and ethical considerations. You will work on adversarial inputs, jailbreaks, and vulnerability discovery while producing actionable data and reproducible reports for customers. This role...Remote job
- Mercor is seeking a remote Red Team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate actionable red team data for safer AI systems. You will annotate failures, classify vulnerabilities, and document risks using established taxonomies...Remote job
- Mercor is seeking a remote Senior Red Team AI Specialist to test conversational agents and AI models against adversarial inputs. You will annotate vulnerabilities, surface systemic risks, and produce reproducible attack cases to help customers strengthen their AI systems...Remote work
- Mercor is assembling a remote red team to test and strengthen AI systems through adversarial inputs. You will annotate failures, classify vulnerabilities, and surface systemic risks using rigorous taxonomies and playbooks. The role rewards clear communication of risks to...Remote job
- Mercor is building a remote red team to probe AI models with adversarial inputs. We focus on testing for jailbreaks, bias and safety vulnerabilities in conversational systems. You will generate actionable data and reports to help customers harden their AI. Ideal candidates...Remote job
- Mercor is building a red team for adversarial AI testing, reviewing outputs on sensitive topics with optional involvement in high-sensitivity projects, guided by clear guidelines and wellness resources. You will red team conversational AI models, generate high-quality human...Remote job
- Mercor is assembling a remote red team to test large language models and AI agents by probing for jailbreaks, prompt injections, and systemic risks. You will work with English and Vietnamese inputs to surface vulnerabilities and produce actionable data for customers. You...Remote job
- Mercor is building a red team for AI safety. This remote role requires English and Dutch fluency and a proactive, adversarial mindset. You will probe conversational AI, annotate vulnerabilities, and generate high-quality attack data for safer deployments. You’ll work across...Remote job
$48 - $62 per hour
...conversational AI systems and produce... ...reproducible adversarial data that... ...improves model safety. This is a text-based red teaming role focused on... ...discovering jailbreaks, prompt injection paths... .... Expand evaluation coverage so... ...Terms Location: Remote. Engagement...Remote workHourly paySaidGig
United States1 day ago$22 per hour
...talent with leading AI research labs.... .... Position: AI Safety Experts — English &... ...hour Location: Remote Role Responsibilities Red team conversational AI... ...Perform jailbreaks, prompt injections, misuse... ...experience in AI adversarial work , cybersecurity...Remote jobContract workSummer work$48 - $62 per hour
...Overview Work as a red team human-data expert... ...conversational AI models and agents... ...The role focuses on adversarial testing, generating... ...including jailbreaks, prompt injections, misuse... ...AI systems Evaluation coverage expands,... ...Terms Location: Remote Employment type...Remote workHourly payFlexible hoursSaidGig
United States1 day ago$17 - $25 per hour
...talent with leading AI research labs.... .... Position: AI Safety Experts — English &... ...hour Location: Remote Role Responsibilities Red team conversational AI... ...Focus on jailbreaks, prompt injections, misuse... ...experience in AI adversarial work , cybersecurity...Remote workContract workSummer work$17 - $25 per hour
...role performs adversarial testing of conversational AI, creating reproducible... ...Red team conversational... ...including jailbreaks, prompt injection, misuse... ...systems Expanding evaluation coverage so... ...in their AI safety because systems... ...Work Terms Remote engagement Hourly...Remote workHourly paySaidGig
United States1 day ago$48 - $62 per hour
...Overview Lead adversarial testing of conversational AI in both English... ...data that helps teams make AI systems... ...Responsibilities Red team... ...including jailbreaks, prompt injections, misuse... ...systems Expanding evaluation coverage so... ...Work Terms Remote engagement, all...Remote workHourly paySaidGig
United States4 days ago$17 - $25 per hour
...Role Overview Join a red team that probes conversational AI with adversarial inputs to find vulnerabilities... ..., jailbreaks, and prompt-injection style... ...structure tests and keep evaluations consistent. Document... ...Work Terms Location: Remote. Employment type: hourly...Remote workHourly paySaidGig
United States3 days ago$29 - $45 per hour
...This role performs adversarial testing of conversational AI to find safety vulnerabilities... ..., human-generated red team data that clients... ...can act on. Work is remote and text-based. The... ...including jailbreaks, prompt injection, misuse... ...systems Expand evaluation coverage so fewer...Remote workHourly paySaidGig
United States3 days ago$48 - $62 per hour
...Overview Work as a human red team specialist probing conversational AI to find vulnerabilities, generate adversarial datasets, and... ...jailbreaks, prompt injections, misuse... ...customer AI systems. Evaluation coverage increases,... ...team. Work Terms Remote, text-based work. Participation...Remote workHourly paySaidGig
United States1 day ago$20 - $22 per hour
...Role Overview Join a remote red team focused on probing conversational AI to find real-world... ...and produce adversarial datasets that improve model safety. You will create and... ...including jailbreaks, prompt injection, misuse scenarios... .... Expanding evaluation coverage so fewer...Remote workHourly paySaidGig
United States3 days ago$24 - $35 per hour
...Overview Join a red team committed to finding... ...in conversational AI. You will probe... ...models and agents with adversarial inputs, document... ...jailbreaks, prompt injections, misuse... ...systems. Increase evaluation coverage so fewer... ...Terms Location: Remote. Employment type...Remote workHourly payShift workSaidGig
United States3 days ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Remote AI Safety Red-Team Evaluator (Adversarial Prompts). Be the first to apply!
Related searches
- program evaluator New York, NY
- work from home web search evaluator New York, NY
- clinical evaluator New York, NY
- evaluator New York, NY
- ai evaluator New York, NY
- work from home social media evaluator New York, NY
- quality evaluator New York, NY
- education evaluator New York, NY
- social media evaluator New York, NY
- operations coordinator remote New York, NY