Stack is at the forefront of developing revolutionary AI and advanced autonomous systems for the trucking industry. Our technology integrates cutting-edge AI, robotics, machine learning, and cloud technologies to create innovative solutions that address the unique challenges of modern trucking operations.
We're seeking a visionary and hands-on technical lead for our ML acceleration team within the ML Platform org. This role will be crucial in designing the architecture and leading a team to automate the optimization and deployment of complex ML models, including transformer-based models like VLMs, for next-gen AI Autonomous Vehicle applications.
The ideal candidate will have a deep understanding of GPUs and optimization, coupled with excellent leadership skills. You'll 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.
Key responsibilities include collaborating with ML researchers to balance model accuracy and speed, leading cross-team projects related to model optimization and deployment, and setting a culture of engineering excellence within the team.
This role offers an exciting opportunity to work at the intersection of AI, autonomous vehicles, and high-performance computing. You'll be part of a team dedicated to pushing the boundaries of what's possible in autonomous trucking, working with cutting-edge technologies and solving complex challenges that have real-world impact.
Join Stack and be part of a diverse, inclusive team that values entrepreneurship and innovation. Together, we're shaping the future of transportation with advanced AI and autonomous systems.