Software Engineer, GPU Inference
Toronto, ONCerebras Systems
5+ YOECerebras Systems needs candidates with 5+ years of software engineering experience, including production inference work for large models. Strong C++ and Python, hands-on serving framework experience such as vLLM, and deep GPU performance knowledge are required.
vLLM, ROCm, PyTorch, Kubernetes, AMD Instinct GPUs, RCCL
Staff Software Engineer, Inference Platform
Toronto, ONCerebras Systems
8+ YOECandidates need 8+ years of software engineering experience, deep distributed systems and Kubernetes expertise, and strong Go or C++ skills. Experience with TLS/mTLS, high-QPS latency optimization, and observability and SLO-driven operations is also required.
Kubernetes, Go, C++
Staff Software Engineer - Tools & Infrastructure / DevOps
Toronto, ONCerebras Systems
7+ YOECandidates need 7+ years of software, infrastructure or DevOps experience, deep hands-on work with CI/CD systems, and experience with cloud platforms and Kubernetes. They also need strong troubleshooting, Linux and scripting skills, and experience leading initiatives across teams.
Kubernetes, AWS
Software Engineer - Tools & Infrastructure / DevOps
Toronto, ONCerebras Systems
4+ YOECandidates need 4 to 8 years in DevOps, infrastructure or software engineering, with hands-on CI/CD, cloud (AWS preferred), Linux and Kubernetes experience. Strong troubleshooting skills and participation in oncall are also expected.
AWS, Kubernetes, Linux, Python, Shell
Software Engineer - New Grad 2026
Toronto, ONCerebras Systems
Candidates need a recent or current computer science or engineering degree graduating in 2026, proficiency in C or C++, and interest or exposure to systems programming, networking, embedded systems or distributed infrastructure.
Embedded systems, ML, Debug software, Debugging, Firmware, Computer science
Senior Software Engineer, ML API – AI Inference
Toronto, ONCerebras Systems
5+ YOECandidates need 5+ years of software engineering experience, strong Python and a production language such as Go, C++ or Rust, and experience building production APIs and operating services on Linux with containers and Kubernetes.
Kubernetes, vLLM, PyTorch, Hugging Face Transformers, LLGuidance, CUDA
Software Engineer - Host and Network IO
Toronto, ONCerebras Systems
3+ YOECandidates need a Master's or PhD in Computer Science or Electrical Engineering with one year of industry experience, or three or more years of industry experience. Strong networking knowledge, socket programming, embedded systems and some driver development are expected.
Wireshark, Arista, Juniper