Machine Learning Security research

My client is a highly funded AI Cybersecurity company with a new approach to securing algorithm's, LLMs, models and AI datasets.

As a Data Scientist specializing in Adversarial Machine Learning, you will be responsible for:

* Identifying and countering existing adversarial attacks on our platform.
* Innovating and publishing novel adversarial attack and defense methodologies.
* Collaborating with a cross-functional team to integrate defenses into customer-facing products.
* Educating the broader technical team on the intricacies and nuances of adversarial ML.

Ultimately, your role will be instrumental in safeguarding customers' ML models, maintaining the companies reputation in the ML community, and pushing the boundaries of knowledge in adversarial machine learning.

WHAT YOU'LL DO:

* Research and detect existing adversarial attacks, implementing countermeasures.
* Design and conduct experiments for new adversarial attacks and their corresponding defenses.
* Collaborate with product teams to integrate findings and solutions into our platform.
* Publish findings, techniques, and methodologies in top-tier machine learning conferences and journals.
* Mentor junior team members and promote a culture of continuous learning and innovation within the adversarial ML space.

WHO YOU ARE:

* Proven track record of published research in adversarial ML or related domains.
* Strong coding skills and familiarity with machine learning frameworks such as TensorFlow or PyTorch.
* Experience in either productionizing models directly or working with members of an ML Engineering team to get work into production.