AI Safety Experts — English & Odia | $20-$22/hr Remote
Overview
We're assembling a red team of human experts to stress-test conversational AI models for safety vulnerabilities. This remote, text-based position requires native fluency in English and Odia. You'll attack AI systems with adversarial inputs, uncover weaknesses, and generate the high-quality data needed to make AI safer. The work covers sensitive topics like bias and misinformation, with clear guidelines and wellness support available.
What You'll Do4
- 1Probe conversational AI models and agents with jailbreaks, prompt injections, and other adversarial techniques to expose flaws.
- 2Generate high-quality human feedback data by annotating model failures, categorizing vulnerabilities, and flagging systemic risks.
- 3Apply structured frameworks, taxonomies, and benchmarks to keep red team testing consistent and reproducible.
- 4Document your findings in clear reports and datasets that give customers actionable insights into their AI systems.
Requirements6
- 1Native fluency in English and Odia is required for this role.
- 2Hands-on experience in red teaming, whether through AI adversarial work, cybersecurity, or socio-technical probing.
- 3A curious and adversarial mindset, comfortable pushing systems to their breaking points.
- 4A structured approach to testing, using frameworks or benchmarks rather than random attempts.
- 5Strong written and verbal communication to explain risks clearly to technical and non-technical audiences.
- 6Flexibility to adapt quickly across different projects, customers, and content types.
Who Should Apply
You're the type of person who loves breaking things to make them better, and you understand that probing AI's weak spots is how we build trust. You're methodical in your work, but creative in your attacks, and you can keep your cool when the content gets sensitive. Whether you come from cybersecurity, adversarial ML, or even a background in psychology, writing, or acting, you bring a fresh perspective to the red team.
Salary Insight
$20.00 - $22.00 per hour, remote and hourly.
Location
Required Skills
Application Tip
In your pitch, share a specific example of a time you found a vulnerability in an AI system or app, and outline the steps you took. That will show your red team mindset better than a list of keywords.
See NearSkill jobs more often in your search
How your application is processed
1Application received
Your resume and details are logged the moment you apply.
2ATS + eligibility screening
We check your profile against the role’s skills, seniority, and requirements.
3Employer sees qualified profiles only
Only candidates who clear screening move forward.
Similar open positions
Explore active roles that match your skills and interests.
Mercor
VerifiedAI Safety Experts — English & Bengali
This role brings fluent English and Bengali speakers into a remote AI red team. You'll probe conversational AI systems with adversarial inputs to uncover biases, misinformation, and manipulation risks. All work is text-based, and you'll produce structured red team data that improves AI safety. You can opt out of higher-sensitivity topics, and clear guidelines plus wellness resources are provided.
Mercor
VerifiedAI Safety Experts — English & Assamese
Mercor is assembling a remote red team of human experts to attack AI models with adversarial inputs. This role focuses on conversational AI, using native English and Assamese to probe for jailbreaks, prompt injections, and bias exploitation. You'll generate red team data and vulnerability reports that make AI systems safer for customers. The work is entirely text-based, with optional participation in higher-sensitivity projects supported by clear guidelines and wellness resources. Hourly compensation is $20-$22.
Mercor
VerifiedAI Safety Experts — English & Punjabi
Join a remote red team that stress-tests AI models for safety vulnerabilities. You will probe conversational AI with adversarial inputs, uncover weak spots like jailbreaks or bias, and turn those findings into data that makes AI safer for customers. Native-level fluency in English and Punjabi is a must. The work is fully text-based and paid hourly, with optional exposure to sensitive topics supported by clear guidelines.
Mercor
VerifiedAI Safety Experts — English & Malay
This remote role asks bilingual experts in English and Malay to stress-test AI systems by simulating attacks and probing for weak points. You'll generate high-quality red team data that helps customers build safer, more trustworthy models. All work is text-based, and sensitive topics are clearly disclosed with wellness support.
Mercor
VerifiedAI Safety Experts — English & Finnish
We're assembling a specialized team to stress-test AI systems by simulating adversarial attacks. As an AI Safety Expert, you'll probe conversational models for vulnerabilities like bias, misinformation, and harmful behaviors — all while working remotely on an hourly basis. Native fluency in both English and Finnish is essential for this role.
Mercor
VerifiedAI Safety Experts — English & Norwegian
This remote role invites fluent English and Norwegian speakers to join an elite red team probing AI models for vulnerabilities. You'll simulate adversarial attacks, document exploits, and generate high-quality human data that directly strengthens AI safety. The work is text-based and focuses on sensitive topics like bias and misinformation, with optional high-sensitivity projects supported by clear guidelines.