AI Inference Core Infrastructure Software Engineer
Summary
Design and maintain Python-based infrastructure for AI inference, focusing on distributed execution, scheduling, and resource management systems. You will build abstractions for workflow planning and failure recovery while defining maintainable APIs for engineering workflows.
You will design, build, test, and maintain Python infrastructure frameworks and services. You will develop scheduling, distributed execution, resource-management, testing, and workflow systems; define maintainable APIs; debug complex distributed issues; and write reliable tests and documentation.
Responsibilities
- Design, develop, test, and maintain Python frameworks and services for engineering workflows
- Build abstractions for scheduling, distributed execution, resource management, test execution, workflow planning, and failure recovery
- Define APIs, module boundaries, extension points, and data models
- Manage concurrency, asynchronous execution, retries, cancellation, and partial failures
- Debug issues across applications, operating systems, filesystems, networking, remote machines, and distributed services
- Write automated tests and documentation
- Translate cross-functional requirements into scalable software designs
Requirements
- 3+ years of professional software-engineering experience
- Strong Python proficiency
- Experience designing maintainable software systems, libraries, frameworks, backend services, or APIs
- Understanding of software architecture, abstraction boundaries, design patterns, and extensibility
- Understanding of concurrency concepts
- Understanding of operating systems and distributed-systems concepts
- Debugging and problem-solving skills





