Description:

Stack is focused on AI advancements across diverse technical domains, transforming how AI is applied in the physical realm.
The training and deployment team is part of the ML Platform org at Stack AV, responsible for the platform that helps the AI team build, optimize, test, and deploy models on autonomous vehicles.
The ML acceleration team is seeking an experienced and hands-on engineer with a deep understanding of GPUs and optimization.
Responsibilities include analyzing and profiling ML models to identify performance bottlenecks, enhancing the platform with OSS tooling, automating model export to optimized formats, implementing optimizations using CUDA and Triton, and collaborating with ML researchers to balance model accuracy and speed.
Key responsibilities involve developing efficient model export and optimization solutions, collaborating with cross-functional teams, staying updated with ML inference technologies, identifying performance bottlenecks, and promoting engineering excellence within the team.

Requirements:

A Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field is required.
A minimum of 5 years of experience, including GPU programming and optimization, is necessary.
Strong programming skills in C++ and Python are essential.
Proven experience in GPU programming and optimization is required.
Familiarity with deep learning frameworks, especially PyTorch, is necessary.
Experience with CUDA programming, Triton language for GPU kernels, PyTorch optimization techniques, TensorRT implementation, ONNX model conversion and deployment, and custom GPU kernel development is required.
A deep understanding of GPU architectures and performance optimization is essential.
Strong analytical and problem-solving skills are necessary.
Excellent verbal and written communication skills are required, with the ability to convey complex technical concepts to non-technical stakeholders.

Stack is committed to being an equal opportunity workplace, promoting diversity and inclusion across various dimensions.
The company fosters a culture of entrepreneurship and innovation.
Employees will have the opportunity to work on cutting-edge AI technology and contribute to advancements in the field.
The position may offer remote work flexibility, allowing for a better work-life balance.
Employees will be part of a team that values engineering excellence and collaboration.