Description:

Contribute to the development of the Everywhere Inference platform, which is a Kubernetes-based solution enabling scalable and portable AI inference across various environments.
Design and implement APIs and developer tools to simplify the deployment, management, and monitoring of AI applications.
Focus on packaging and integrating new machine learning models into the platform, utilizing Python and common ML frameworks.
Optimize serverless container workflows for AI workloads, ensuring performance, scalability, and seamless autoscaling.
Collaborate with customers to fine-tune machine learning model performance and support their unique use cases.
Work with cross-functional teams to enhance the AI applications marketplace and ensure smooth model onboarding and lifecycle management.
Stay current with trends in Kubernetes, machine learning, and MLOps, and help drive innovation within the platform.

Requirements:

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

Competitive compensation is offered to all employees.
Flexible working hours and hybrid or remote options are available, depending on the role.
Employees can work from anywhere in the world for up to 45 days per year.
Private medical insurance is provided for employees and their families.
Extra paid vacation and sick leave days are included.
Support for life’s important moments and celebrations is available.
Language courses are offered to help employees connect and grow.
Modern, welcoming offices are equipped with snacks, drinks, and entertainment.
Team sports and social activities are organized for employees.
Note: Benefits may vary depending on the employee's location.

Skills