Senior Backend Engineer, Inference Cloud

About the role

Cerebras Systems builds the world's largest AI chip, delivering training and inference speeds over 10 times faster than GPU-based cloud services. It is hiring a senior backend engineer to build and scale the services behind Cerebras Inference Cloud, which supports the Developer Console and lets developers and enterprises access, manage and run inference workloads. The role suits a backend generalist who works across services, APIs, databases and data pipelines.

Key responsibilities

• Take end-to-end ownership of backend systems such as billing, usage metering, quotas, account management, request logs and metrics.
• Design and implement APIs, backend services and data pipelines for the Developer Console and other cloud systems.
• Define service boundaries, data models and processing patterns, balancing consistency, real-time and batch processing, performance and cost.
• Build integrations between customer-facing workflows, internal services and infrastructure, with clear contracts and robust handling of failures and retries.
• Turn ambiguous needs into concrete designs, break down the work and deliver solutions that grow with customer usage.
• Improve observability, debugging, testing and recovery, and investigate production issues.
• Guide design reviews, mentor engineers and coordinate execution across teams.
• Work with frontend engineers and other stakeholders to turn customer needs into dependable backend capabilities.

Required profile

• Typically 8+ years of industry experience building and operating production software.
• Bachelor's or master's degree in computer science, or equivalent practical experience.
• Experience designing, delivering and operating complex production systems, owning their behavior after launch.
• Relevant experience in cloud platforms, developer tools, billing and metering systems, identity and access management, observability or high-volume data processing.

Required skills

• Strong backend fundamentals: APIs, services, data models, distributed systems, concurrency, consistency, caching and failure handling.
• Database and data-processing experience: designing schemas, query performance, transactional and asynchronous workflows.
• Experience with GraphQL, Postgres and Redis is helpful.