Software Engineering • Mid-Level

Who you are

You have a strong background in software engineering with a focus on infrastructure development — your experience includes building and maintaining complex systems that support machine learning applications. You are proficient in Python and Go, and you understand the intricacies of deploying scalable applications in cloud environments.

You have hands-on experience with Kubernetes — you've implemented and maintained Kubernetes deployments, ensuring high availability and performance for model serving. Your familiarity with multi-cloud environments allows you to manage resources efficiently across different platforms.

You are a problem solver who enjoys tackling challenges related to resource management and performance monitoring — you have developed monitoring systems that provide insights into model performance metrics, enabling teams to make data-driven decisions.

You thrive in collaborative environments — you work closely with cross-functional teams to implement technical solutions that enhance deployment workflows and improve the overall efficiency of machine learning operations. Your communication skills help you articulate complex technical concepts to non-technical stakeholders.

Desirable

Experience with ML inference platforms or similar technologies is a plus — you understand the unique challenges associated with deploying machine learning models in production. Familiarity with GPU resource management and orchestration is also beneficial.

What you'll do

As an Infrastructure Software Engineer at Baseten, you will develop infrastructure components for our ML inference platform — your work will enable developers to deploy, scale, and monitor machine learning models effectively. You will contribute to the core infrastructure, ensuring that it meets the high-performance demands of production AI applications.

You will implement and maintain Kubernetes deployments for model serving, ensuring that our systems are robust and scalable. Your contributions to the inference orchestration layer will facilitate seamless model deployments, allowing teams to focus on building innovative AI products.

You will build and enhance monitoring systems that track model performance metrics — this will involve developing solutions that provide real-time insights into the health and efficiency of our machine learning workloads. Your expertise in resource management will help optimize the use of GPUs and other resources, ensuring that our infrastructure can handle varying workloads efficiently.

You will support infrastructure automation initiatives to improve ML deployment workflows — your work will streamline processes, reduce manual intervention, and enhance the overall developer experience. You will collaborate with team members to implement technical solutions that drive efficiency and effectiveness in our operations.

What we offer

At Baseten, we are committed to fostering a diverse and inclusive workplace — we provide equal employment opportunities to all employees and applicants. You will be part of a collaborative and forward-thinking team that is dedicated to building cutting-edge AI products. We offer competitive compensation and benefits, along with opportunities for professional growth and development in a rapidly evolving industry.