The opportunity
Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services.
What you'll do
Design and develop software features that support system resiliency and high: availability, including automated recovery mechanisms and fault-tolerant architecture across distributed environments.
Develop and maintain cloud-based deployment workflows for AI inference: software using AWS tools and services to support low-latency and scalable system performance.
Develop Python-based scripts and APIs to streamline data preprocessing,: inference execution, and post-processing for real-time inference tasks.
Use parallel programming techniques (e.g., multi-threading, asynchronous: processing) to maximize resource efficiency on AWS compute instances.
Develop software components to support visualization and analysis of system: performance metrics, enhancing the monitoring and usability of inference services.
Develop inference software in Docker containers and define Kubernetes: orchestration strategies that ensure software reliability and efficient scaling.
What they're looking for
- Develop automated scripts to detect and mitigate common failure modes, improving software system reliability.
- Debug issues related to model deployment, container orchestration, and: networking configurations, documenting steps to reproduce and root-cause defects.
- Triage and resolve defects in the software service by analyzing logs,: metrics, and distributed traces using tools like AWS CloudWatch, Grafana, or custom Python scripts.
- Work with Product Management and User Experience teams to define requirements: for inference service interfaces, including configuration, monitoring, and event logging.
