Software Engineering

Who you are

You have a strong background in software engineering with a focus on building and optimizing APIs for AI models. Your experience includes working with distributed systems and model serving, ensuring that the infrastructure you create is both reliable and efficient. You are familiar with advanced inference capabilities and understand the intricacies of structured outputs and multi-modal serving.

You possess expertise in performance profiling and optimization, particularly with TensorRT and CUDA. Your ability to analyze kernel performance and implement custom CUDA operators allows you to maximize throughput and optimize memory allocation patterns. You thrive in collaborative environments and are eager to contribute to a forward-thinking team.

What you'll do

In this role, you will design, build, and operate the Model APIs surface, focusing on advanced inference capabilities. You will profile and optimize TensorRT-LLM kernels, analyze CUDA kernel performance, and implement custom CUDA operators. Your work will involve tuning memory allocation patterns for maximum throughput and optimizing communication patterns across multi-GPU setups. You will collaborate closely with product and model performance teams to define how developers interact with AI models at scale.

What we offer

At Baseten, you will be part of a rapidly growing company that is at the forefront of AI technology. We provide a diverse and inclusive workplace where your contributions will have a significant impact. You will have the opportunity to work with cutting-edge technologies and be part of a team that is dedicated to pushing the boundaries of AI applications.