Machine Learning Engineer - Secure AI Lab

At the SEI AI Division, we conduct research in applied artificial intelligence and the engineering questions related to the practical design and implementation of AI technologies and systems. We currently lead a community-wide movement to mature the discipline of AI Engineering for Defense and National Security.

As our government customers adopt AI and machine learning to provide leap-ahead mission capabilities, we build real-world, mission-scale AI capabilities through solving practical engineering problems, discover and define the processes, practices, and tools to support operationalizing AI for robust, secure, scalable, and human-centered mission capabilities, prepare our customers to be ready for the unique challenges of adopting, deploying, using, and maintaining AI capabilities, and identify and investigate emerging AI and AI-adjacent technologies that are rapidly transforming the technology landscape.

As a Machine Learning Engineer, you will specialize in engineering solutions that support research into the vulnerabilities of AI and ML algorithms and securing against those vulnerabilities.

The Secure AI Lab within the SEI’s AI Division focuses on improving the security and robustness of AI systems. As part of the world‑class research community at Carnegie Mellon University, the Secure AI Lab conducts and applies cutting‑edge research to protect AI systems from adversaries who aim to manipulate the system to learn, do, or reveal something it isn’t supposed to.

• Counter AI Research:
  Study threat models targeting AI and ML algorithms, understand the behaviors of AI algorithms, identify weak points, and design novel ways to subvert AI and ML systems.
• AI and ML Algorithm Defense Research:
  Create practical mitigations and defenses for observed attacks affecting AI and ML algorithms and evaluate the effectiveness of defensive techniques.
• Applied Adversarial Machine Learning:
  Advance the state of the art in adversarial machine learning by developing and transitioning capabilities to government sponsors.

Your day‑to‑day engineering tasks will include:

• Identifying and investigating emerging AI and AI‑adjacent technologies.
• Defining and refining processes, practices, and tools for working with AI.
• Designing and building well‑engineered prototypes of AI systems.
• Transitioning and providing guidance on AI capabilities to government sponsors.

• Build Machine Learning Models and Systems using frameworks such as Tensor Flow, PyTorch, Torch, and Caffe, and modern programming languages including Python, C/C++, and Java. Build and work with data pipelines, ETL processes, and backend systems; extend and implement state‑of‑the‑art machine learning methods.
• Conduct technical experimentation with modern and emerging machine learning frameworks, methods, and algorithms in application domains that include computer vision, natural language processing, planning and scheduling, robot control, and engineering safe, trusted, and reliable machine learning systems.
• Test and evaluate systems for performance and security; conduct rapid prototyping to demonstrate and evaluate technologies and use novel testing and analysis techniques.
• Collaborate on teams of developers, researchers, designers, and technical leads; work with researchers and government customers to understand challenges, needs, and possible solutions.
• Mentor and teach others, contribute to improving the overall technical capabilities of the Division through design sessions and sharing insights and wisdom.

• Comprehensive knowledge of machine learning; previous experience in adversarial machine learning desirable but not required.
• Track record of using well‑established engineering practices to solve difficult problems.
• Understanding of converting research results into functioning prototypes or capabilities.
• Experience leading technical projects in novel areas with limited previous work to build upon.
• Strong written and verbal communication skills; able to convey complex technical ideas to laypersons.
• Ample experience with publishing written or technical artifacts showcasing your work.
• Strong…