Ai Red Team Specialist - Remote

Mercor; Jakarta Pusat; Remote; IDR 423,417,000 - 622,672,000; Part time

Job summary

Mercor mencari AI Red Team Specialist yang berperan remote untuk menguji keamanan model AI secara menyeluruh. Anda akan melakukan uji coba terhadap perilaku model, mengidentifikasi potensi risiko, dan menghasilkan dataset serta laporan aksi yang dapat digunakan pelanggan.

Posisi ini menuntut kemampuan berbahasa Inggris dan Indonesia secara lancar, pengalaman red teaming pada domain AI, serta kemampuan menjelaskan risiko secara jelas kepada pemangku kepentingan teknis maupun non-teknis.

Qualifications

• Harus fasih berbahasa Inggris dan Indonesia.
• Pengalaman red teaming pada pekerjaan AI adversarial atau cybersecurity diutamakan.
• Kemampuan menjelaskan risiko secara jelas untuk pihak teknis maupun non-teknis.

Responsibilities

• Red team model AI percakapan dan agen; fokus pada jailbreaks, prompt injections, misuse cases, dan bias exploitation.
• Menghasilkan data manusia berkualitas tinggi; mengannotasi kegagalan, mengklasifikasikan kerentanan, dan menandai risiko sistemik.
• Menggunakan taxonomies, benchmarks, dan playbooks untuk menjaga pengujian tetap konsisten.
• Menyusun laporan, dataset, dan kasus serangan yang bisa diterapkan oleh pelanggan secara rekreasional.

Skills

English fluency

Indonesian fluency

Red teaming experience

Risk communication

Job description

AI Red Team Specialist - Remote

Deskripsi Pekerjaan - AI Red Team Specialist - Remote

Perusahaan : Mercor Jenis Pekerjaan : Full-Time Jakarta Jakarta Indonesia

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 & Indonesian
Type: Contract
Compensation: $17–$25/hour
Location: Remote

Role Responsibilities

• Red team conversational AI models and agents. Focus on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.

Qualifications

Must-Have

• Fluent in English and Indonesian.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to explain risks clearly to technical and non-technical stakeholders.

Preferred

• Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• Background in Cybersecurity: penetration testing, exploit development, reverse engineering.
• Knowledge of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.