Senior ML Acceleration Engineer

Stack is at the forefront of developing revolutionary AI and advanced autonomous systems for the trucking transportation industry. Our technology incorporates cutting-edge advancements in artificial intelligence, robotics, machine learning, and cloud technologies to create innovative solutions that enhance safety, reliability, and efficiency of modern operations.

We are seeking an experienced and hands-on engineer for our ML acceleration team within the training and deployment team, part of the ML Platform org at Stack AV. This role is crucial in developing and optimizing the platform that enables our AI team to build, optimize, test, and deploy models on autonomous vehicles.

As an ML Acceleration Engineer, you will be responsible for analyzing and profiling ML models, implementing optimizations using CUDA, Triton, and custom kernels, and automating the process of exporting models to optimized formats like TensorRT. You'll work closely with ML researchers to balance model accuracy and speed, and collaborate with cross-functional teams to understand data requirements and design appropriate solutions.

The ideal candidate will have a deep understanding of GPUs and optimization, excellent collaboration skills, and the ability to drive technical excellence. This role offers an opportunity to work with cutting-edge technologies in the autonomous vehicle industry and make a significant impact on the future of transportation.

Join Stack and be part of a team dedicated to creating an autonomous solution ecosystem tailored to the unique demands of the trucking industry. We offer a diverse and inclusive work environment that values entrepreneurship and innovation across all backgrounds and identities.

Note: This position may be subject to U.S. national security-related requirements and export control regulations. Candidates may need to meet specific residence, U.S. person status, and/or citizenship criteria.