English and Assamese AI Safety Red Teamer
$20 - $22 per hourSaidGig
Help strengthen conversational AI by finding the vulnerabilities that automated testing misses. This remote role focuses on adversarial testing, failure analysis, and creating practical evidence that improves AI safety and reliability. Role Overview
You will test AI models and agents using adversarial inputs, identify weaknesses, and produce structured data and documentation that teams can use to improve their systems. The work may include text-based review of AI outputs involving sensitive subjects, including bias, misinformation, and harmful behavior. Participation in higher-sensitivity work is optional; topics are disclosed before exposure, with clear guidance and wellness resources available.
Key Responsibilities- Test conversational AI models and agents for jailbreaks, prompt injection, misuse cases, bias exploitation, and multi-turn manipulation.
- Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply established taxonomies, benchmarks, and playbooks to keep testing consistent.
- Create reproducible reports, datasets, and attack cases that stakeholders can act on.
- Expand evaluation coverage across scenarios and help reduce unexpected production risks.
- Native fluency in both English and Assamese is required.
- Prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
- Ability to use structured frameworks or benchmarks for adversarial testing.
- Clear communication skills for explaining risks to technical and non-technical audiences.
- Comfort adapting across projects and stakeholders.
- Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attacks, or model extraction.
- Cybersecurity, including penetration testing, exploit development, or reverse engineering.
- Socio-technical risk analysis, such as harassment or misinformation probing, abuse analysis, or conversational AI testing.
- Creative adversarial thinking informed by psychology, acting, or writing.
- Remote, hourly engagement.
- $20 to $22 per hour.
Vacancy posted 1 day ago
Similar jobs that could be interesting for youBased on the English and Assamese AI Safety Red Teamer in United States vacancy
- Mercor is seeking an AI Safety Expert to remotely assess and fortify AI systems. You will red-team conversational models, identify jailbreaks and biases, and generate... ...data to help customers mitigate risks. Strong English and Swedish communication is essential, with prior...English language skillsRemote jobContract workFlexible hours
$20 - $22 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ...and Jack Dorsey . Position: AI Safety Experts — English & Assamese Type: Contract Compensation:... ...Remote Role Responsibilities Red team conversational AI models and...English language skillsContract workSummer workRemote workMercor
San Francisco, CA6 days ago$70 - $84 per hour
...Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors... ...Adam D'Angelo , Larry Summers , and Jack Dorsey . Position AI Safety Red Teamer Type Contract Compensation $70-$84/hour Location Remote Role...SuggestedContract workSummer workRemote work- Handshake is seeking an AI Red Teamer in Seattle, WA, to stress-test large language models by designing adversarial prompts. The role involves... ...collaborating with a multidisciplinary team to strengthen AI safety. Ideal candidates should have strong experience with LLMs, an...Suggested
- We are seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across complex, high-risk, and ambiguous ("grey-area"...Suggested
$20 - $22 per hour
...performs adversarial testing of conversational AI systems, probing models for vulnerabilities and producing reproducible red team data that helps make AI safer. Work is... ...22 hourly Eligibility Native fluency in English and Odia is required Ability to perform remote...English language skillsHourly payRemote workSaidGig
United States1 day ago$20 - $22 per hour
...Role Overview You will join a red team of human experts who probe conversational AI to uncover vulnerabilities and produce reproducible attack data. The role... ...act on Qualifications Native fluency in both English and Bengali, spoken and written, is required Prior...English language skillsHourly payRemote workSaidGig
United States1 day ago$17 - $25 per hour
...adversarial testing of conversational AI, creating reproducible attack... .... Key Responsibilities Red team conversational AI models... ...probing Native fluency in English and Indonesian, both required... ...customer confidence in their AI safety because systems have been thoroughly...English language skillsHourly 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 with adversarial inputs to surface... ...red team data that improves model safety. This text-based role focuses on... ...Native fluency in both English and Vietnamese is required Prior...English language skillsHourly payRemote workSaidGig
United States4 days ago$17 - $25 per hour
...Role Overview Join a red team that probes conversational AI with adversarial inputs to find vulnerabilities before they reach customers. This text-... ...25 hourly. Eligibility Native fluency in both English and Malay is required. Candidates must be able to work...English language skillsHourly payRemote workSaidGig
United States4 days ago$29 - $45 per hour
...performs adversarial testing of conversational AI to find safety vulnerabilities and produce reproducible, human-generated red team data that clients can act on. Work is... ...socio-technical probing Native fluency in English and Portuguese, with the Portuguese variety being...English language skillsHourly payRemote workSaidGig
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... ...adversarial datasets that improve model safety. You will create and document... ...Eligibility ~ Native fluency in both English and Punjabi is required for this...English language skillsHourly payRemote workSaidGig
United States1 day ago- Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design prompts, uncover model weaknesses, and assess safety across high-risk topics. Join a cutting-edge research environment,...
- Mercor is seeking an AI Safety Red Teamer to design adversarial prompts and stress-test frontier AI models in a remote contract role. The candidate will identify jailbreaks, unsafe behaviors, hallucinations, and policy failures while evaluating robustness across misinformation...Remote jobContract work
$24 - $35 per hour
...Overview Help strengthen conversational AI systems by testing them as an adversary would... ...for vulnerabilities, create actionable red-team data, and evaluate text-based outputs... ...Qualifications Native fluency in both English and Thai is required. Prior red-teaming...English language skillsHourly payRemote workSaidGig
United States23 days ago$48 - $62 per hour
...Role Overview Probe conversational AI systems for safety and misuse vulnerabilities in both English and Norwegian, producing high-quality adversarial test cases, annotations... ...automated tests miss. Key Responsibilities Red team conversational AI models and agents,...English language skillsHourly payRemote workSaidGig
United States23 days ago- ...Overview Probe conversational AI systems with adversarial inputs... ...vulnerabilities, produce reproducible red-team data, and deliver... ...focused on rigorous, structured safety testing across multiple projects... ...Eligibility Native fluency in both English and Danish is required Role...English language skillsHourly payRemote work
SaidGig
United States23 days ago $29 - $45 per hour
Mercor connects elite creative and technical talent with leading AI research labs. The AI Safety Experts — English & Portuguese (global) contract role is remote, offering $29-$45/hour. You will red team conversational AI models, generate high-quality human data, and document...English language skillsRemote jobContract work- A technology firm is seeking an AI Red-Teamer for adversarial AI testing. The ideal candidate will be fluent in English and Chinese (Mandarin) and have prior experience in red teaming, cybersecurity, or adversarial testing. The role involves red teaming conversational AI...English language skillsRemote jobHourly payContract work
- ...Fluent Language Skills Required English & Punjabi. Native fluency in... ...Mercor, we believe the safest AI is the one that’s already been... ...attacked — by us. We are assembling a red team for this project - human... ...Mercor customers trust the safety of their AI because you’ve already...English language skillsRemote work
- Mercor is seeking a remote red-team data expert to probe AI models with adversarial inputs, surface vulnerabilities... ...-quality data for safer AI systems. English and Thai fluency are required, with... ...across projects for robust safety testing. This role focuses on reproducible...English language skillsRemote 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...English language skillsRemote job
- Mercor is seeking an AI Safety Expert to join a remote contract team. You will red team conversational AI, identify jailbreaks, and analyze biases to improve model safety. You will generate high-quality data, annotate failures, and document findings with actionable reports...English language skillsRemote jobContract work
$48 - $62 per hour
...creative and technical talent with leading AI research labs. Headquartered in San... ..., and Jack Dorsey . Position: AI Safety Experts — English & Danish Type: Contract Compensation... ...Remote Role Responsibilities Red team conversational AI models and...English language skillsContract workSummer workRemote workMercor
San Francisco, CA12 days ago- 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...English language skillsRemote job
- Mercor is building a remote AI red team to probe and test conversational models for vulnerabilities, bias, and safety gaps. This role emphasizes reproducible data and actionable findings across projects and customers. You bring prior red teaming experience in AI or cybersecurity...English language skillsRemote job
$20 - $22 per hour
...AI Safety Experts — English & Assamese 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...English language skillsRemote jobFor contractors10 hours per week$48 - $62 per hour
...Role Overview Probe conversational AI systems and produce reproducible adversarial... ...vulnerabilities and improves model safety. This is a text-based red teaming role focused on discovering... ...hour. Eligibility ~ Native fluency in English and Swedish is required....English language skillsHourly payRemote workSaidGig
United States5 days ago$65 per hour
A leading AI consulting firm is seeking an AI Tutor specialized in Coding. This part-time freelance role involves evaluating AI models... ...tools. You must hold a relevant degree, possess advanced English skills, and have experience in scripting, containerization, and...English language skillsRemote jobPart timeFreelanceFlexible hours$48 - $62 per hour
...Role Overview Work as a human red team specialist probing conversational AI to find vulnerabilities, generate adversarial datasets, and produce reproducible... ...guidance. Qualifications Native fluency in English and Danish is required. Prior red teaming experience...English language skillsHourly payRemote workSaidGig
United States5 days ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to English and Assamese AI Safety Red Teamer. Be the first to apply!
Related searches
- english translator United States
- english speaking United States
- english language art teacher United States
- bilingual customer service representative spanish english United States
- english part time United States
- teach english online part time United States
- assistant professor of english United States
- english United States
- english full time jobs United States
- teach english online no degree United States