while improving AI model performance. Qualifications Must-Have Native fluency in English and Gujarati. Strong judgment...-technical audiences. Adaptability across projects, task types, and customers. Preferred Experience with Adversarial ML...
with technical and non-technical audiences. Adaptability across projects, task types, and customers. Preferred Adversarial ML...: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction. Cybersecurity: penetration testing, exploit...
while improving AI model performance. Qualifications Must-Have Native fluency in English and Bengali. Strong judgment..., task types, and customers. Preferred Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO...
. Adaptability to move across projects and customers. Preferred Experience in Adversarial ML: jailbreak datasets, prompt... injection, RLHF/DPO attacks, model extraction. Cybersecurity: penetration testing, exploit development, reverse engineering...
-technical stakeholders. Preferred Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks..., model extraction. Cybersecurity skills: penetration testing, exploit development, reverse engineering. Socio-technical...
while improving AI model performance. Qualifications Must-Have Native fluency in English and Kannada. Strong judgment... across projects, task types, and customers. Preferred Experience with Adversarial ML, Cybersecurity, and socio-technical risk...
while improving AI model performance. Qualifications Must-Have Native fluency in English and Bengali. Strong judgment..., task types, and customers. Preferred Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO...
while improving AI model performance. Qualifications Must-Have Native fluency in English and Gujarati. Strong judgment...-technical audiences. Adaptability across projects, task types, and customers. Preferred Experience with Adversarial ML...
while improving AI model performance. Qualifications Must-Have Native fluency in English and Kannada. Strong judgment... across projects, task types, and customers. Preferred Experience with Adversarial ML, Cybersecurity, and socio-technical risk...
with technical and non-technical audiences. Adaptability across projects, task types, and customers. Preferred Adversarial ML...: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction. Cybersecurity: penetration testing, exploit...