Remote AI Safety Specialist: Adversarial Testing & Risk
$20 - $22 per hourMercor
New York, NY
- Remote job
Mercor is seeking AI Safety Experts fluent in English & Telugu for remote contract work. The role involves red teaming conversational AI models to identify risks and improve model performance. Ideal candidates have experience in AI adversarial work or cybersecurity and can explain risks to diverse stakeholders. Compensation is set at $20–$22/hour with flexible working hours. Apply now to join the innovative team at Mercor! #J-18808-Ljbffr Mercor
Vacancy posted 4 days ago
Similar jobs that could be interesting for youBased on the Remote AI Safety Specialist: Adversarial Testing & Risk in New York, NY vacancy
$20 - $22 per hour
...talent with leading AI research labs.... ...Details Position: AI Safety Experts — English... ...2/hour Location: Remote Role Responsibilities... ...and flag systemic risks. Apply structure... ...consistent testing. Document reproducibly... ...experience in AI adversarial work , cybersecurity...Remote jobRiskContract workSummer work$22 per hour
...talent with leading AI research labs.... ...Position: AI Safety Experts — English... ...hour Location: Remote Role Responsibilities... ...and flag systemic risks. Apply... ...maintain consistent testing. Document reproducibly... ...experience in AI adversarial work ,...Remote jobRiskContract workSummer work$22 per hour
...talent with leading AI research labs.... ...Position: AI Safety Experts — English... ...hour Location: Remote Role Responsibilities... ...and flag systemic risks. Apply... ...playbooks for consistent testing. Document reproducibly... ...experience in AI adversarial work ,...Remote jobRiskContract workSummer work$22 per hour
...talent with leading AI research labs.... ...Position: AI Safety Experts — English... ...hour Location: Remote Role Responsibilities... ...flagging systemic risks. Apply... ...ensure consistent testing. Document reproducibly... ...in red teaming (AI adversarial work,...Remote jobRiskContract workSummer work- Mercor is seeking AI Safety Experts proficient in English and Kannada to join their remote team. This role involves red teaming AI... ...addressing vulnerabilities in adversarial machine learning. Candidates... ...and the ability to communicate risks effectively. The position...Remote jobRiskHourly pay
$20 - $22 per hour
Mercor is seeking AI Safety Experts fluent in English and Assamese to work remotely. The role involves red teaming... ...experience in AI adversarial work and strong communication... ...skills to explain risks effectively. The ideal... ...approach to testing AI systems. #J-18808-...Remote jobRiskHourly pay$28.74 per hour
...Compensation: $28.74/hour Location: Remote Role Responsibilities Red team conversational AI models and agents (jailbreaks,... ..., and flagging systemic risks. Apply structured taxonomies,... ...playbooks to ensure consistent adversarial testing. Produce reproducible reports,...Remote jobRiskHourly payFull timeContract workPart time- Obsidian is seeking a remote AI red team expert responsible... ...AI models with adversarial inputs to uncover vulnerabilities... ...will apply structured testing frameworks, document... ...data to improve AI safety. The ideal candidate... ...skills to explain risks effectively. Join us to...Remote jobRisk
$148.5k - $223.9k
## Adversarial AI & Research EngineerApplyremote type: Remote Home-Basedlocations: California - Remote: Washington... ...teams, we mitigate risk across all AI... ...tooling, and foundational testing methodologies for both... ...Familiarity with current AI safety research and frameworks...Remote workRiskShift work$26 per hour
...26/hour Location: Remote Commitment: 10-40... ...team conversational AI systems using... ...exploitation, and multi-turn adversarial strategies.... ...flagging systemic risks. Follow structured... ..., benchmarks, and testing playbooks to ensure... ...with defined safety guidelines. Requirements...Remote jobRiskHourly payContract work$50 - $90 per hour
.../hourpay Role Title: AI Safety & Red Teaming Specialist Role Type: Contractor Location: Remote We are looking for an... ...leverage your expertise in adversarial AI, LLM security, and... ...ethical jailbreak testing, prompt injection... ...and prompt injection risks. Create comprehensive...Remote workRiskFor contractorsWeekday work- ...Artificial Intelligence (AI) Consultant to... ...England with some remote flexibility, you... ...on progress, risks, and key decisions... ...supporting reviews, testing and validation activities... ...with technical specialists, business... ...operational contexts, safety, or regulatory constraints...Remote workRiskFull time
American Bureau of Shipping
United States3 days ago - Mercor is seeking an AI Safety Expert who is proficient in both English and Punjabi to join their remote team. The role involves red teaming conversational... ...and effectively communicating risks. The ideal candidate has prior experience in AI adversarial work and cybersecurity,...Remote jobRiskContract work
$20 - $22 per hour
Mercor is seeking AI Safety Experts who are fluent in English and Malayalam... ...AI research labs. This remote contract role involves red... ...candidates will have experience in adversarial AI and cybersecurity, with... ...skills to explain risks effectively to both technical...Remote jobRiskHourly payContract work$20 - $22 per hour
Mercor is seeking AI Safety Experts with fluency in English and Marathi to join our team remotely. The role involves identifying vulnerabilities... ...valuable data for risk assessment. Successful candidates... ...a strong background in AI adversarial work, cybersecurity, and the...Remote jobRiskHourly pay- ...Salesforce, Inc. is seeking an Adversarial AI & Research Engineer for a remote role focused on the intersection of... ...AI. This position involves leading testing to discover vulnerabilities, innovating... ...ability to communicate technical risks effectively. Join us to redefine...Remote workRisk
Salesforce
Austin, TX3 days ago - ...A progressive technology company is seeking a remote AI Red Teamer to assess conversational AI models and identify vulnerabilities... ...Brazilian Portuguese, with a background in cybersecurity or adversarial testing. This role involves producing actionable reports and datasets...Remote workHourly pay
Crossing Hurdles
New York, NY1 day ago $50.5 per hour
Position: AI Red-Teamer — Adversarial AI Testing (Advanced); English & Chinese (Mandarin) Type: Hourly contract... ...Compensation: $50.5/hour Location: Remote Commitment: Hourly Contract Role... ...vulnerabilities, and flagging systemic risks. Apply structured taxonomies,...Remote jobRiskHourly payContract work- Mercor is seeking AI Safety Experts for remote work to red team conversational AI models. Candidates will focus on identifying vulnerabilities,... ...fluent in English and Kannada and have prior experience in AI adversarial work or cybersecurity. This role involves collaborating...Remote job
- ...Staff AI Security Engineer Remote; United States Blink Health is the fastest growing healthcare... ...lead the security, governance, and risk management of AI at BlinkRx, from enterprise... ...AI lifecycle, lead red-teaming and adversarial testing of AI systems, and serve as the...Remote workRisk
Blink Health
United States3 days ago - ...about the BUSINESS) The Responsible AI Scaled Testing Team within Trust & Safety performs pre-launch structured... ...in operations, strategy, ethics, risk management, product management, and... ...moderation, red teaming, AI testing, adversarial testing, or similar. 1+ years...Remote workRisk
Varite
United States7 hours ago $134k - $171k
...EMCOR Group, Inc. seeks an AI Security Engineer who... ..., governance, risk management, and hands-on... ...and maintain AI security testing capabilities such as prompt... ...behavior evaluations, adversarial testing, etc. Work with... ...Location Type Remote Posted Date 1 week...Remote workRiskFull timeFlexible hoursEMCOR Group
Phoenix, AZ4 days ago$84.91k - $113.91k
...Center for Cyber Safety and Education, enables... ...about cyber risks and empowering access... ...Position Summary The AI Security Engineer... ...products for adversarial threats, model vulnerabilities... ..., adversarial testing, and of LLM-based... ...Locations US-Remote Posted Date 2...Remote workRiskWork experience placementWork at officeNight shiftISC2
Atlanta, GA1 day ago$100.17k - $145k
...Technologies seeks an innovative remote AI-Enabled Solutions Developer to... ...with stakeholders Debug, test, and refine AI-generated code... ...deliverables, procurement, staffing, and risk tracking Experience working... ...that puts people’s safety and well-being first. Regardless...Remote workRiskFull timeContract workWork experience placementWork at officeLocal areaWorldwide$20 - $22 per hour
...talent with leading AI research labs.... ...Dorsey. Position AI Safety Experts — English... ...22/hour Location: Remote Role Responsibilities... ...and flag systemic risks. Apply structure... ...maintain consistent testing. Document... ...experience in AI adversarial work, cybersecurity...Remote workRiskContract workSummer workMercor Inc
San Francisco, CA1 day ago- ...radar network and AI-enabled analytics platform... ...assets, monitors adversarial behavior, and... ...redefining global security, safety, and transparency... ...version control, testing, and CI/CD Strong... ...initial low‑risk improvements such as... ...workforce: flexible remote/hybrid opportunities...Remote workRiskFlexible hours
Alumni Ventures
Menlo Park, CA7 hours ago - NTT DATA is seeking an AI Evaluation & Testing (Eval Engineer) to... ...Core Responsibilities Adversarial Testing (Red Teaming)... ...effectively with remote and cross‑functional... ...LangSmith, Ragas; AI safety and red teaming experience... ...scope. Third‑party risk assessment and SOC 2...Remote workRiskFor subcontractor
$106.5k - $159.5k
...operation of the enterprise AI Governance framework to... ..., transparent, and risk-managed across their... ...lifecycle. The AI Governance Specialist partners with IT, Legal... ...with pre-deployment testing and post-deployment... ...However, we are also open to remote candidates located...Remote workRiskFlexible hoursSmith & Nephew
Andover, MA1 day ago- ...Location : Remote Fluent Language Skills... ...the safest AI is the one that's... ...probe AI models with adversarial inputs, surface vulnerabilities... ...and flag systemic risks - Apply... ...playbooks to keep testing consistent... ...customers trust the safety of their AI because...Remote workRisk
Mercor Alabaster
United States7 hours ago - ...is expanding its **AI Center of... ...and is hiring a **Specialist Solutions Engineer... ...explain AI security testing results**—particularly... ...Model behavior under adversarial or ambiguous... ...define **acceptable risk thresholds** and success... ...@f5.com.**Remote**: Primarily work...Remote workRiskWork at officeLocal areaWork from home
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Remote AI Safety Specialist: Adversarial Testing & Risk. Be the first to apply!
Related searches
- ai data scientist New York, NY
- ai scientist New York, NY
- program coordinator remote New York, NY
- research coordinator remote New York, NY
- automation engineer remote New York, NY
- remote ui developer New York, NY
- remote customer service advisor New York, NY
- it manager remote New York, NY
- remote financial planning New York, NY
- junior angular developer remote New York, NY