AI Safety Specialist - Fully Remote | Up to $22/hr

mercor; India; Remote; INR 2,095,000 - 2,881,000; Full time

Job summary

Mercor connects elite creative and technical talent with leading AI research labs. The AI Safety Experts role is remote and contract-based, requiring native fluency in English and Assamese, with the flexibility to work asynchronously.

You will red team conversational AI models, annotate failures, and document findings to help customers improve safety, reliability, and performance of their systems.

Qualifications

• Native fluency in English and Assamese.
• Strong judgment about language and content accuracy.
• Rigorous attention to subtle errors and inconsistencies.
• Ability to work to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects and task types.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases for customer action.
• Work independently and asynchronously to enhance AI model performance and ensure flexible hours.

Skills

English fluency

Assamese fluency

Quality judgment

Attention to detail

Communication skills

Adaptability

Job description

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.

Position: AI Safety Experts — English & Assamese
Type: Contract
Compensation: $16-22/hour
Location: Remote

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases for customer action.
• Work independently and asynchronously to enhance AI model performance and ensure flexible hours.

Qualifications

Must-Have

• Native fluency in English and Assamese.
• Strong judgment about language and content accuracy.
• Rigorous attention to subtle errors and inconsistencies.
• Ability to work to guidelines and quality standards.
• Clear communication with technical and non-technical audiences.
• Adaptability across projects and task types.

Preferred

• Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks.
• Knowledge in Cybersecurity: penetration testing, exploit development, reverse engineering.
• Understanding of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
• Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.