Remote AI Reliability & Red Team Engineer

Technopals Pte.; Polska; Híbrido; PLN 61 000 - 113 000; Tempo integral

Resumo da oferta

Technopals Pte.Ltd. is seeking a skilled ML Engineer to lead the technical stress-testing of AI systems, focusing on adversarial robustness, bias detection, and mitigation of hallucinations. The role emphasizes proactive red teaming and continuous monitoring in a remote setup.

You will design adversarial attacks, build the monitoring stack, and collaborate with Data Scientists to apply fairness techniques when bias is identified, ensuring reliable model behavior.

Qualificações

• BS/MS in Data Science, Mathematics, or Cybersecurity.
• 4+ years in ML Engineering with a focus on model security or reliability.
• Expert Python skills; deep experience with PyTorch, TensorFlow, and MLOps pipelines.

Responsabilidades

• Red Teaming: Design and execute adversarial attacks against LLMs and predictive models.
• Automated Monitoring: Build and maintain the Continuous Control stack using tools like Evidently AI or WhyLabs.
• Bias Remediation: Collaborate with Data Scientists to implement algorithmic fairness techniques when bias is detected.

Conhecimentos

Python

PyTorch

TensorFlow

MLOps

Formação académica

BS/MS in Data Science, Mathematics, or Cybersecurity

Ferramentas

Evidently AI

WhyLabs

Descrição da oferta de emprego

Technopals Pte.Ltd. is seeking a skilled ML Engineer to lead the technical stress-testing of AI systems, focusing on adversarial robustness, bias detection, and mitigation of hallucinations. The role emphasizes proactive red teaming and continuous monitoring in a remote setup.

You will design adversarial attacks, build the monitoring stack, and collaborate with Data Scientists to apply fairness techniques when bias is identified, ensuring reliable model behavior.