Director, AI Alignment and Interpretability Remote - CrowdStrike

Key Responsibilities

• Lead cross‑functional teams to design, prototype, and deploy AI alignment and interpretability frameworks that safeguard the security platform.
• Conduct cutting‑edge research on bias mitigation, explainability, and adversarial robustness in machine learning models.
• Collaborate with product, engineering, and policy groups to embed ethical AI principles into the product roadmap.
• Define metrics, benchmarks, and evaluation pipelines for alignment and interpretability performance.
• Mentor and grow a high‑performing team of researchers, data scientists, and software engineers.

Requirements

• PhD or equivalent experience in AI, machine learning, or related fields with a focus on alignment, interpretability, or ethics.
• Proven track record of publishing in top AI conferences or journals.
• Hands‑on experience with deep learning frameworks (PyTorch, TensorFlow) and large‑scale data pipelines.
• Strong communication skills and ability to translate complex research into actionable product features.
• Experience in cybersecurity or high‑stakes domains is a plus.