Post-Doctoral Associate

The Software and Societal Systems Department, in the School of Computer Science, and Carnegie Mellon University has an opening for a Post-Doctoral position.

The postdoc will contribute to two main projects: developing machine-learning-based anomaly detection for industrial control systems AND developing a verification and validation platform for AI-based drone software. The tasks and responsibilities will involve formulating specific research questions and hypotheses to advance these projects; developing novel algorithms for anomaly detection, for identifying adversarial-example-based vulnerabilities in drone control software, and for making drone control software more robust to adversarial examples; designing and carrying out experiments to test the proposed algorithms; analyzing data collected during experiments; writing technical reports and scientific papers; an preparing presentations for both highly technical and less technical audiences. The postdoc also will supervise and mentor one or more PhD, masters, or undergraduate students; and they will participate in applying for additional research funds, e.g., by contributing to writing funding proposals.

The candidate must have a PhD in computer science or a related field. 5-plus years of research experience. Significant research experience both in machine-learning-based anomaly detection and in ML-based aerial vehicle control, as evidenced by one or more publications in each area. Experience writing and presenting research papers and writing reports for and preparing and delivering presentations to sponsors. Experience supervising and mentoring MS students. Expertise and 2+ years of experience with deep learning frameworks (e.g., PyTorch and Tensorflow), MATLAB simulation frameworks, and data analysis frameworks (e.g., numpy, scikit-learn, pandas). Ability to deliver results under pressure, to work independently, to develop project plans, and to clearly communicate results in written and oral form.

Please provide CV, writing statements, research statements, publications.