Description:

Baseten is a growing team of builders backed by top-tier investors, focusing on machine learning performance.
The company provides ML infrastructure for enterprises and AI-native companies, ensuring performance, security, and reliability.
The Software Engineer - ML Performance role is designed for individuals passionate about advancing artificial intelligence.
The position is ideal for backend engineers who enjoy optimizing processes and are interested in open-source ML models.
Responsibilities include implementing and refining techniques for ML model inference, debugging performance issues, applying optimization techniques, collaborating with a diverse team, and managing projects from idea to production.

Requirements:

A Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or a related field is required.
Candidates must have 3+ years of professional work experience in a fast-paced, high-growth environment.
Proficiency in one or more general-purpose programming languages, such as Python, C++, or Go, is necessary.
A deep understanding of software engineering principles and experience in developing and deploying AI/ML inference solutions is essential.
Strong familiarity with ML libraries, particularly PyTorch, TensorRT, or TensorRT-LLM, is required.
Candidates should demonstrate interest and experience in machine learning and large language models.
A deep understanding of GPU architecture is necessary.
Experience with Docker and Kubernetes is required.
Experience and interest in growing and leading a team is highly valued.

The position offers a competitive compensation package, including unlimited PTO, 401k, and covered healthcare premiums.
Employees have a unique opportunity to be part of a rapidly growing startup in an exciting engineering field.
The company promotes an inclusive and supportive work culture that fosters learning and growth.
Employees gain exposure to a variety of ML startups, providing unparalleled learning and networking opportunities.

Skills