AI Inference Core - Senior Infrastructure Software Engineer

The role

You will design and build core software for engineering infrastructure. This includes working on Python frameworks, orchestration systems, distributed execution, scheduling, test infrastructure, and developer tooling.

What you will do

• Design, develop, test, and maintain Python frameworks and services to orchestrate engineering workflows.
• Build reusable abstractions for scheduling, distributed execution, resource management, test execution, workflow planning, and failure recovery.
• Define APIs, module boundaries, extension points, and data models.
• Reason about concurrency, asynchronous execution, multiprocessing, state management, retries, idempotency, cancellation, and partial failures.
• Debug complex issues spanning Python applications, operating systems, processes, filesystems, networking, remote machines, and distributed services.
• Write high-quality automated tests and documentation.
• Partner with platform, CI, release, quality, ML systems, and product engineering teams.

Required qualifications

• 5+ years of professional software-engineering experience.
• Strong proficiency in Python and understanding of the language's strengths, limitations, and runtime behavior.
• Experience designing maintainable software systems, libraries, frameworks, backend services, or developer-facing APIs.
• Good judgment around software architecture, abstraction boundaries, design patterns, extensibility, and long-term maintainability.
• Understanding of concurrency concepts such as processes, threads, asynchronous execution, synchronization, and shared state.
• Foundational understanding of operating systems, including processes, signals, filesystems, resource management, and program execution.
• Foundational understanding of distributed-systems concepts such as retries, timeouts, idempotency, partial failure, coordination, and eventual consistency.
• Strong debugging and problem-solving skills.

Nice to have

• Experience with Python concurrency technologies such as asyncio, multiprocessing, concurrent futures, or event-driven systems.
• Experience building orchestration engines, workflow systems, schedulers, distributed job runners, or control-plane software.
• Experience developing test infrastructure or extensions for frameworks such as pytest.
• Familiarity with CI systems, build systems, release infrastructure, or developer-productivity tooling.
• Experience with Kubernetes, containerized environments, cluster schedulers, or remote execution systems.
• BS/MS in Computer Science or a related field, or equivalent practical experience.

Benefits

• Build a breakthrough AI platform beyond the constraints of the GPU.
• Publish and open source cutting-edge AI research.
• Work on one of the fastest AI supercomputers in the world.
• Job stability with startup vitality.
• Simple, non-corporate work culture that respects individual beliefs.

About the company

Cerebras Systems builds the world's largest AI chip. The company works with leading model labs, global enterprises, and cutting-edge AI-native startups.