Remote AI Red Team Safety Specialist: Adversarial Testing
Obsidian
San Francisco, CA
- Remote job
Mercor is seeking a remote red-team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate high-quality data for safer AI systems. English and Thai fluency are required, with topics ranging from bias to harmful content handled under clear guidelines. You’ll document results and collaborate across projects for robust safety testing. This role focuses on reproducible artifacts, standardized taxonomies, and cross-functional communication to stakeholders, #J-18808-Ljbffr Obsidian
Vacancy posted 4 hours ago
Similar jobs that could be interesting for youBased on the Remote AI Red Team Safety Specialist: Adversarial Testing in San Francisco, CA vacancy
- Obsidian is seeking a remote AI red team expert responsible for probing AI models with adversarial inputs to uncover vulnerabilities. You will apply structured testing frameworks, document findings, and generate... ...-quality data to improve AI safety. The ideal candidate brings...Remote job
$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... ...is required, along with prior experience in adversarial AI testing or cybersecurity. This is a flexible hourly commitment...Remote jobHourly payFor contractors10 hours per weekFlexible hours$26 per hour
...$26/hour Location: Remote Commitment: 10-40 hours... ...Responsibilities Red-team conversational AI systems using jailbreaks... ..., and multi-turn adversarial strategies. Generate... ...taxonomies, benchmarks, and testing playbooks to ensure... ...with defined safety guidelines. Requirements...Remote jobHourly payContract work- ...progressive technology company is seeking a remote AI Red Teamer to assess conversational AI... ...identify vulnerabilities through red teaming exercises. Candidates should be fluent... ...with a background in cybersecurity or adversarial testing. This role involves producing...Remote workHourly pay
Crossing Hurdles
New York, NY2 days ago $60 - $90 per hour
...LLM Red Team Specialist — Failure Modes & Edge Cases is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure... ...rubric clause it violated so the safety team can patch the gap. Why this...Remote jobFor contractors10 hours per week- ...Capability Elicitation Red Team Specialist is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure... ...the rubric clause it violated so the safety team can patch the gap. Why this role matters...Remote jobHourly payFor contractors10 hours per week
- 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 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
$20 - $22 per hour
...Probe conversational AI systems for vulnerabilities and help strengthen their safety through adversarial testing, structured evaluation, and clear, reproducible findings. This remote, hourly role focuses on text-based AI red teaming in both English and Punjabi. Role Overview...Remote workHourly paySaidGig
United States8 days ago$48 - $62 per hour
...Overview Probe conversational AI systems for safety and misuse vulnerabilities... ..., producing high-quality adversarial test cases, annotations, and... ...Key Responsibilities Red team conversational AI models and... ...Work Terms Remote engagement Hourly employment...Remote workHourly paySaidGig
United States22 days ago- Location Remote Fluent Language Skills Required... ...the safest AI is the one that’s... ...are assembling a red team for this project -... ...probe AI models with adversarial inputs, surface vulnerabilities... ...playbooks to keep testing consistent... ...trust the safety of their AI because...Remote work
$20 - $22 per hour
...talent with leading AI research labs.... .... Position: AI Safety Experts — English &... ...hour Location: Remote Role Responsibilities Red team conversational AI... ...maintain consistent testing. Document reproducibly... ...red teaming, AI adversarial work ,...Remote workContract workSummer workMercor
New York, NY7 days ago- ...Overview Probe conversational AI systems with adversarial inputs to expose... ...vulnerabilities, produce reproducible red-team data, and deliver... ...harmful behaviors. This is a remote, text-based role focused on rigorous, structured safety testing across multiple projects and...Remote workHourly pay
SaidGig
United States22 days ago $29 - $45 per hour
...talent with leading AI research labs.... .... Position: AI Safety Experts — English &... ...hour Location: Remote Role Responsibilities Red team conversational AI... ...maintain consistent testing. Document reproducibly... ...experience in AI adversarial work ,...Remote workContract workSummer workMercor
New York, NY10 days ago$121.9k - $197.1k
What You'll Do The Adversarial Red Team Associate Principal is responsible for... ...in OSINT, penetration testing, C2 infrastructure development... ...detection capabilities. Leverage AI/LLM tooling to accelerate... ...environment, up to 2 days per week of remote work. Tuition reimbursement...Remote workWork at office2 days per week- OneZero Solutions is seeking a Red Team Operator to support the Coast Guard engagement in... ...Alexandria, VA. The role involves conducting adversary simulations, building attacker... ...techniques, C2 frameworks, and security testing across cloud and on-prem environments. On...
- ...Senior Advisor - Red Team Lead at Southern California... ...this job, you’ll:Adversary Emulation... ...understanding of safety and reliability constraints... ...(including AI/ML) to scale Red Team... ..., penetration testing, and vulnerability... ...the option to work remotely on the remaining days...Remote workRelocation
$60 - $90 per hour
...talent with leading AI research labs.... ...Cybersecurity SWE — AI Safety Type: Contract... ...Location: Remote Commitment:... ...with AI research teams to improve model safety... ..., penetration testing, vulnerability research... ..., grading, or red-teaming technical content...Remote workFull timeContract workSummer workImmediate startMercor
Remote14 hours ago$145.9k - $234.2k
...execute, and evolve advanced adversarial simulation campaigns to test Moderna’s cyber resilience... ...with a focus on AI and the attack surface it... ...This role reports to the Red Team Program Lead and works very... ...Cambridge, Massachusetts; Remote - US; DigitalType: Full timeRemote workPermanent employmentFull timeWork at officeWork from home$48 - $62 per hour
...Overview Work as a human red team specialist probing conversational AI to find vulnerabilities, generate adversarial datasets, and produce reproducible... ...Adversarially test conversational AI models and... ...human team. Work Terms Remote, text-based work. Participation...Remote workHourly paySaidGig
United States4 days ago$20 - $22 per hour
...Role Overview Join a remote red team focused on probing conversational AI to find real-world vulnerabilities and produce adversarial datasets that improve model safety. You will create and document targeted... ...Perform adversarial testing of conversational AI and agents...Remote workHourly paySaidGig
United States4 days ago$48 - $62 per hour
...Role Overview Lead adversarial testing of conversational AI in both English and Norwegian,... ...human-labeled data that helps teams make AI systems safer. All... ...Key Responsibilities Red team conversational AI models... ...risks Work Terms Remote engagement, all work is text...Remote workHourly paySaidGig
United States4 days ago$24 - $35 per hour
...Role Overview Join a red team committed to finding real... ...vulnerabilities in conversational AI. You will probe models and agents with adversarial inputs, document... ...to ensure consistent testing and coverage. Produce... ...Work Terms Location: Remote. Employment type: hourly...Remote workHourly payShift workSaidGig
United States3 days ago- ...is seeking a research-focused professional to join a GenAI red-team within a leading AI lab network. The role involves probing frontier models,... ...findings for reproducibility. This full-time W-2 position is remote within the United States, requiring about 35 hours per...Remote workFull time
$60 - $90 per hour
...continuous, focused effort. You will work remotely with researchers in a tight feedback... ..., research engineering, security, or AI evaluation. Proven ability to... ...modes in LLMs or ML systems through red teaming, adversarial testing, security research, or rigorous model...Remote workHourly payFull timeFreelanceSaidGig
United States3 days ago- ...within Google Cloud, seeks an experienced Red Team Consultant to assess and advise clients... ...red and purple team assessments and adversarial emulation to identify weaknesses and improve... ...and internal wireless, web, and mobile testing, threat analysis, and producing clear reports...Remote work
Google
Peru, IL19 hours 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 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 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
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Remote AI Red Team Safety Specialist: Adversarial Testing. Be the first to apply!
Related searches
- ai data scientist San Francisco, CA
- ai scientist San Francisco, CA
- senior devops engineer remote San Francisco, CA
- medical coding remote San Francisco, CA
- remote medical coding supervisor San Francisco, CA
- remote virtual San Francisco, CA
- remote contract attorney San Francisco, CA
- clinical data manager remote San Francisco, CA
- administrative assistant remote San Francisco, CA
- remote animation San Francisco, CA