Software Engineer - Host and Network IO
Cerebras Systems21 hours ago
Toronto, Canada or Sunnyvale, CA, USAMid Level
H1B sponsor
Responsibilities
- Develop x86 and ARM software exposing hardware I/O capabilities for AI and HPC application teams.
- Govern a generic I/O API used by multiple internal teams.
- Develop control and configuration subsystems that interact directly with Cerebras hardware.
- Debug network performance in large AI clusters and analyze statistics and packet traces to identify bottlenecks.
- Develop telemetry and tools that improve visibility into network and I/O datapaths.
- Optimize CPU and memory utilization using kernel-bypass and zero-copy techniques.
- Integrate networking technologies and protocols.
- Lead cross-functional technical projects spanning software and hardware teams.
- Communicate effectively with teams and stakeholders.
Requirements
- Master’s or PhD in Computer Science or Electrical Engineering plus one year of industry experience, or three-plus years of industry experience.
- Experience working in large software environments.
- Experience with embedded systems, hardware/software co-design, and some driver development.
- Familiarity with TCP, RoCE, and network debugging tools such as Wireshark, or willingness to learn.
- Familiarity with network switch environments such as Arista and Juniper, or willingness to learn.
- Strong analytical attention to detail and willingness to learn broader systems and unfamiliar areas.
Benefits
- Opportunity to build software and hardware for a large-scale AI platform beyond GPU constraints.
- Opportunities to publish and open-source AI research.
- Work on a high-performance AI supercomputer.
- Job stability with startup vitality.
- A simple, non-corporate work culture that respects individual beliefs.
- Equal-opportunity and inclusive work environment focused on learning, growth, and support.
Categories
About Cerebras Systems
Cerebras Systems designs and sells AI compute systems built around its wafer-scale WSE-3 processor, delivered as the CS-3 appliance and via the Cerebras Cloud. It targets enterprises, model labs, and government users needing fast training and inference, and offers on‑prem and cloud deployments. Privately held and headquartered in Sunnyvale, California, the company announced a multi-year partnership with OpenAI to deploy large-scale inference capacity.