Software Engineering

Who you are

You have a strong background in software engineering with a focus on machine learning performance — your experience includes optimizing ML models and working with open-source frameworks. You thrive in collaborative environments and are eager to contribute to innovative AI solutions. Your technical expertise allows you to dive deep into codebases and implement cutting-edge techniques for model inference.

You are familiar with various ML optimization techniques such as quantization and speculative decoding — you understand the importance of performance in deploying AI models at scale. Your passion for artificial intelligence drives you to stay updated with the latest advancements in the field, and you are excited about the potential of large language models (LLMs).

What you'll do

As a Software Engineer at Baseten, you will be responsible for implementing and refining techniques that enhance ML model performance — this includes working on projects like the Baseten Embeddings Inference and the Baseten Inference Stack. You will collaborate with a dynamic team to drive model performance optimization and ensure that the infrastructure supports high-speed inference.

You will engage with the underlying codebases of frameworks such as TensorRT and PyTorch, contributing to the development of efficient solutions for AI applications. Your role will involve productionizing advanced techniques that improve the speed and efficiency of model inference, making significant contributions to the company's mission of enabling AI companies to bring their models into production seamlessly.

What we offer

At Baseten, we provide a supportive and inclusive work environment where innovation thrives. You will have the opportunity to work on mission-critical projects that impact leading AI companies. We encourage you to apply even if your experience doesn't match every requirement, as we value diverse perspectives and backgrounds. Join us in shaping the future of AI technology.