About this role
The team is seeking a Staff Software Engineer specializing in Inference and Compute Infrastructure Engineering. In this role, you will be responsible for building and managing systems that treat infrastructure as software. You will own the software state machines that provision hardware, bring it into service, and manage its full lifecycle, transforming racks of GPUs into operational inference clusters without manual intervention.
Key Responsibilities:
- Develop and maintain software systems for infrastructure management.
- Create and optimize state machines for hardware provisioning and lifecycle management.
- Collaborate closely with the Research and Inference team to understand their needs and improve their workflows.
- Implement API solutions that allow seamless scaling and management of inference clusters.
- Troubleshoot and resolve issues related to infrastructure and software integration.
Required Skills & Qualifications:
- Proficiency in programming languages such as Python, Go, or similar.
- Strong experience with cloud infrastructure and orchestration tools (e.g., Kubernetes, AWS).
- Familiarity with GPU architecture and inference workloads.
- Experience in building and managing scalable software systems.
- Excellent problem-solving skills and the ability to work collaboratively in a team environment.
Experience:
- Minimum of 5 years of relevant experience in software engineering, with a focus on infrastructure or systems development.
What we offer:
- An opportunity to work on cutting-edge technology in a dynamic environment.
- A collaborative and innovative team culture.
- Opportunities for professional growth and development.
Applications are read by our talent team, usually within two working days.
If you look like a fit we will call you, and you will hear from us either way.