AI Jailbreak & Prompt-Injection Security Expert

Àwọn Ìjánu-ìsún Àwọn Àṣẹ Àkóónú Ìṣàmúlò-ètò

Fi àtòjọ-ẹ̀yàn ìṣàmúlò-ètò hàn (English) Àwọn ìṣàfarawé

Àwọn Àkọ́lé

A leading AI data lab is engaging AI Jailbreak & Prompt-Injection Security Experts to contribute to a cutting-edge customer initiative focused on AI safety and robustness. In this role, you'll apply your expertise to help train next-generation AI systems. Your work will shape how models learn, reason, and perform through high-quality, real-world input. No prior experience in AI is required - your domain knowledge is what matters.

Role Type: Contractor | Location: Remote | Pay: $50 - $90/hour

How to Apply
Email your resume to drashti.hiring@gmail.com with the subject "AI Jailbreak Security Expert".

Àwọn Ìkúndùǹ

- 2+ years of expertise in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security domain.
- Proven experience researching, testing, or uncovering vulnerabilities related to ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
- Advanced degree (PhD, MS) in computer science, cybersecurity, machine learning, or a relevant discipline, or equivalent operational/professional background.
- High credibility within the AI security or adversarial ML community, such as published research, open-source tools, or conference presentations.
- Exceptional written and verbal communication skills, with a strong focus on clear documentation and collaborative problem-solving.
- Prior participation in multi-disciplinary projects or cross-functional AI safety initiatives is a plus.
- Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is highly desirable.s,

Àwọn Àṣẹ

- Design and implement advanced methodologies for evaluating AI system safety, focusing on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse scenarios.
- Create comprehensive cross-domain elicitation strategies to uncover multi-turn and complex adversarial bypass patterns in AI models.
- Develop, maintain, and update regression test suites that systematically test for jailbreak susceptibility and prompt-injection vulnerabilities.
- Construct robust evaluation frameworks that stress-test AI models against real-world adversarial threats, aiming to enhance overall system robustness.
- Collaborate with technical stakeholders to translate security findings into actionable improvements for model safety and risk mitigation.
- Document methodologies, findings, and best practices in clear, well-structured written reports and presenta

Àwọn Ìmọ̀ Ìṣàmúlò-ètò

Ethical Jailbreaks, LLM Red Teaming, Prompt Injection, Tool-Use Abuse

Àwọn Àtòjọ-ẹ̀yàn Àwọn Àtòjọ-ẹ̀yàn

Àwọn ìṣàmúlò-ètò $50 - $90/hr

Àwọn Ìṣàmúlò-ètò: 2 ọdun

Fipalẹ̀: 6 hours, 27 minutes Àwọn àwọn ààyè-iṣẹ́

Àwọn Àwòrán 168

Fi wọlé láti fi ṣẹ́

Gba ìṣàmúlò-ètò tí a tí ìṣàmúlò-ètò náà fún ààyè-iṣẹ́ yìí

Fi ìwé ìwé rẹ̀ lọ́wọ́lọ́wọ́, a si kọ́ ìwé ìwé kan ti a fi hàn ìwé yi - ọ̀fẹ̀, àti tí a tí wa níbẹ̀ nígbà tí a bá kọ́ àkọ́kọ́ rẹ̀.

PDF, Wẹ́ẹ̀bù tàbí àkọ́lé. A tí kọ́ àwọn àwọn iroyin ọ̀fẹ́ rẹ̀ nínú ojú-ìwé tókàn - kò si kaadi.

Ṣàfihàn fún iṣẹ́ bí a ṣè?

Fi iṣẹ́ rẹ̀ tí o tí ìyàn lọ́wọ́lọ́wọ́ pamọ́ sí WFHJ ki o si gbà awọǹ àtílẹ̀̀ tí a tí ìdáràn. Kò ní owó.

Fi iṣẹ́ hàn — ọ̀fẹ́