AI Safety Experts — English & Assamese | $20-$22/hr Remote
Overview
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.
What You'll Do5
- 1Run adversarial attacks on conversational AI models, including jailbreaks, prompt injections, misuse cases, and multi-turn manipulations.
- 2Produce high-quality human data by annotating model failures, classifying vulnerabilities, and flagging systemic risks.
- 3Follow established taxonomies, benchmarks, and playbooks to keep red team tests consistent and repeatable.
- 4Document attack cases and datasets so product teams can reproduce findings and take action.
- 5Optionally join higher-sensitivity content reviews with advance notice, clear topic descriptions, and wellness support.
Requirements4
- 1Native-level fluency in English and Assamese, both written and spoken.
- 2Hands-on red teaming experience from AI adversarial work, cybersecurity, or socio-technical probing.
- 3A structured approach to testing, using frameworks or benchmarks rather than random hacks.
- 4Comfort explaining technical risks to both engineering and non-technical stakeholders.
Who Should Apply
You're the kind of person who instinctively looks for the edge cases in any system. You've spent time pushing AI models to their limits, whether through jailbreak datasets, penetration testing, or creative adversarial thinking. You're methodical enough to document every finding and curious enough to explore unconventional attack paths. You communicate clearly and you're comfortable shifting between different projects and customer needs.
Salary Insight
$20.00 - $22.00 per hour, depending on the project assignment.
Location
Required Skills
Application Tip
When you apply, include a one-paragraph breakdown of a specific red team attack you executed, the vulnerabilities you uncovered, and how you presented those findings to the team.
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 & Odia
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.
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 & 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.
Mercor
VerifiedAI Safety Experts — English & Indonesian
Neon is looking for bilingual AI safety experts fluent in English and Indonesian to join a human-driven red team. You'll probe advanced conversational AI models for vulnerabilities like bias, misinformation, and harmful behavior — all through text-based work. This remote, hourly role pays $17–$25/hr and gives you a direct hand in making AI systems safer before they reach the public.
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.