Staff Software Engineer, GPU Inference at Cerebras Systems

Department: Software Engineering

Language

Setup: Hybrid
Location: Toronto, Ontario
Type: Full-time
Level: senior
Posted: Jul 28, 2026

Description

Cerebras Systems is hiring a Software Engineer to productionize and optimize its GPU inference serving stack. The role covers GPU prefill and decode services, vLLM, PyTorch, ROCm, AMD GPU infrastructure, deployment and operational readiness, reliability, performance optimization, numerical correctness, debugging, and benchmarking infrastructure. Candidates need at least 8 years of software engineering experience, strong C++ and Python skills, production inference-system experience, and a bachelor’s degree or equivalent practical experience.

Required Skills

C++
Python
vLLM
ROCm
Distributed systems
GPU execution
Kubernetes
Observability
CI/CD
Numerical correctness

Additional Information

Minimum Education: Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline, or equivalent practical experience.
Required Previous Experiences: 8+ years of software engineering experience, including substantial individual-contributor ownership of complex production systems.
Experience building, operating, or optimizing production inference systems for large language models, multimodal models, or similarly demanding GPU workloads.
Hands-on experience with a high-performance model-serving framework such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, or an equivalent internally developed system.
Experience debugging distributed systems across multiple layers rather than treating the serving framework or accelerator runtime as a black box.
Experience with Linux, containers, Kubernetes or comparable orchestration systems, observability, CI/CD, and operating latency-sensitive services in production.
Preferred Qualifications: Experience with AMD Instinct accelerators and the ROCm ecosystem.
Deep CUDA experience and ability to transfer GPU systems knowledge across accelerator platforms.
Experience modifying or contributing to open-source ML systems projects.
Experience optimizing prefill-heavy or disaggregated prefill/decode inference architectures.
Understanding of KV-cache transfer, prefix caching, continuous batching, chunked prefill, request scheduling, and memory-aware admission control.
Experience with multi-GPU and multi-node inference, including parallelism and failure handling.
Experience optimizing Mixture-of-Experts or multimodal models.
Knowledge of GPU kernel optimization, operator fusion, graph capture, attention kernels, GEMM tuning, and communication/computation overlap.
Experience with reduced-precision inference and quantization formats.
Experience building numerical-comparison, determinism, model-validation, or performance-regression test systems.
Experience collaborating with accelerator vendors, framework maintainers, or open-source communities.