Bilingual AI Safety Red Team Analyst — Remote

Obsidian; Sydney; Remote; AUD 127,000 - 183,000; Full time

Job summary

Mercor is assembling a remote AI safety red team focused on testing conversational models with adversarial inputs, bias checks, and content probes. The role requires strong judgment of language and content in English and Malayalam, with rigorous attention to detail and a structured, guideline-driven approach.

You will generate reproducible data and attack case reports, contributing to safer AI for customers while collaborating with cross-functional teams in a flexible, remote environment.

Qualifications

• Strong judgment about language and content, able to judge accuracy and appropriateness.
• Rigorous attention to subtle errors, inconsistencies, and gaps.
• Ability to follow guidelines and quality standards consistently.

Responsibilities

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation.
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document reproducibly: produce reports, datasets, and attack cases customers can act on.

Skills

Adversarial ML

Cybersecurity

Risk analysis

Written communication

Structured thinking

Adaptability

English proficiency

Malayalam language

Job description

Mercor is assembling a remote AI safety red team focused on testing conversational models with adversarial inputs, bias checks, and content probes. The role requires strong judgment of language and content in English and Malayalam, with rigorous attention to detail and a structured, guideline-driven approach.

You will generate reproducible data and attack case reports, contributing to safer AI for customers while collaborating with cross-functional teams in a flexible, remote environment.