The Machine Learning Engineer specializing in DNS Security Research will develop models, processes, and systems to consolidate and analyze diverse "big data" sources related to the security, stability, and resiliency (SSR) of the Domain Name System (DNS). They will utilize statistical and machine learning techniques to extract insights and address research questions. The role involves communicating findings to management and the wider community to contribute to SSR security-related decision-making.

Responsibilities:

• Collect, curate, and analyze data sources related to SSR of DNS.
• Design and implement scalable and efficient data pipelines and storage solutions.
• Develop software programs, machine learning algorithms, and custom data models for cleansing, integrating, and evaluating large datasets.
• Optimize code and algorithms to utilize high-performance computing capabilities.
• Implement parallel computing techniques to distribute data and computation for improved performance and scalability.
• Analyze large and complex datasets to identify patterns, trends, and anomalies related to internet identifiers' security.
• Use machine learning and deep learning modeling (if needed) to enhance DNS Abuse detection and decision-making for SSR of DNS.
• Conduct in-depth data analyses and produce high-quality visualizations and reports.
• Identify research gaps and questions related to SSR of DNS and collaborate with teams and communities.
• Coordinate with different teams to implement models and monitor outcomes.
• Interpret and communicate insights and findings from analysis and experiments.

Required Knowledge, Skills, and Abilities (KSAs):

• Strong knowledge and experience in machine learning and AI techniques.
• Ability to develop and implement custom algorithms for complex DNS SSR problems.
• Knowledge of model deployment techniques and monitoring model performance and accuracy.
• Familiarity with high-performance computing clusters (Hadoop, Spark) for large-scale workloads.
• Understanding of explainable AI techniques for transparency and accountability.
• Experience in data visualization to communicate insights effectively.
• Familiarity with cloud computing platforms and scaling machine learning workflows.
• Proficiency in programming languages like Python and machine learning frameworks (TensorFlow, PyTorch, Scikit-Learn).
• Strong understanding of data parallelism techniques for optimizing machine learning workflows.
• Excellent written and verbal communication skills.
• Ability to manage multiple projects and deliver high-quality results.
• Contributions to the research community through publications.

Education and Experience Requirements:

• MSc or PhD in Mathematics, Physics, Computer Science, Security, Engineering, or related field.
• Minimum 5+ years of work experience in machine learning engineering and relevant fields such as statistics. Require 3 + years’ experience with a PhD Degree.
• Hands-on experience with machine learning frameworks (TensorFlow, PyTorch, Scikit-Learn).
• Minimum 3 years of experience in designing and implementing scalable machine learning workflows.
• Prior international experience preferred.
• Experience in cybersecurity, particularly internet identifier security, is a plus.

• Fluency in written and spoken English is required. Additional languages are a plus.

Working Conditions & Physical Requirements:

• International travel may be required for ICANN meetings, approximately three times per year.
• Availability for domestic and international travel, sometimes with limited notice.
• Comfortable working in an international environment with flexible availability.
• Office-based work with limited privacy and some exposure to background noise.
• Occasional lifting and/or moving of up to 25 pounds may be required.

***PLEASE INCLUDE A MOTIVATIONAL LETTER WITH YOUR RESUME. COMBINE IT WITH YOUR OTHER DOCUMENTS INTO ONE ATTACHMENT***