Remote Software Python Engineer (Cloud Inference)

Description:

• The Software Python Engineer will contribute to the development of the Everywhere Inference platform, which is a Kubernetes-based solution for scalable and portable AI inference across various environments.
• Responsibilities include designing and implementing APIs and developer tools to simplify the deployment, management, and monitoring of AI applications.
• The role focuses on packaging and integrating new machine learning models into the platform using Python and common ML frameworks.
• The engineer will optimize serverless container workflows for AI workloads, ensuring performance, scalability, and seamless autoscaling.
• Collaboration with customers is essential to fine-tune ML model performance and support unique use cases.
• The engineer will work with cross-functional teams to enhance the AI applications marketplace and ensure smooth model onboarding and lifecycle management.
• Staying current with trends in Kubernetes, machine learning, and MLOps is crucial to drive innovation within the platform.

Requirements:

• Proficiency in Python, particularly in the context of machine learning tooling or backend development, is required.
• Experience with AI/ML pipelines or integrating machine learning frameworks like TensorFlow or PyTorch into production environments is necessary.
• Hands-on experience with vLLM and SGLang is expected.
• Familiarity with cloud-native tooling such as Docker, Helm, and related CNCF technologies is required.
• A problem-solving mindset and a genuine interest in working on distributed systems and platform-level challenges are essential.
• Clear communication skills and a collaborative attitude are necessary, as the role involves working closely with others to build effective solutions.
• Nice to have: Solid experience with Go programming, particularly in Kubernetes, including building controllers, operators, and working with custom resources (CRDs).
• A strong understanding of Kubernetes architecture, container orchestration, and resource management at scale is beneficial.
• Understanding of GPU scheduling and performance optimization in Kubernetes is a plus.
• Awareness of Kubernetes security practices, including RBAC and container hardening, is advantageous.
• Contributions to open-source projects or involvement in cloud-native or MLOps communities are desirable.

Benefits:

• The position offers a competitive salary.
• Flexible working hours are provided to accommodate different schedules.
• Employees can choose remote, hybrid, or office work options depending on their role.
• The opportunity to work from anywhere in the world for up to 45 days per year is available.
• Private medical insurance is offered for employees and their families.
• Employees receive 5 additional vacation days.
• Additional fully paid sick leave days are provided.
• An allowance for significant life events and birthdays is included.
• Language classes are available to support professional development.
• The company offers a modern office space with free snacks, drinks, and entertainment options.
• Team sports activities are organized to promote team bonding and wellness.