Build and optimize Cerebras’s production GPU inference stack across APIs, vLLM, PyTorch, ROCm, distributed systems, and AMD infrastructure. The role requires 8+ years of software engineering experience, strong C++ and Python skills, and deep expertise in GPU performance, reliability, and model serving.
Characterize, analyze, and optimize performance of state-of-the-art AI models on Cerebras' wafer-scale hardware. Build performance models, optimize kernels and compilers, debug runtime behavior, and develop visualization tools to influence next-gen AI architecture.
Own model quality and performance for Cerebras inference by building AI agent-driven eval suites, automating benchmarking, and creating customer-specific tooling. Requires strong AI agent experience and tooling intuition.
Senior Performance Engineer benchmarks Cerebras inference performance against competitors for real workloads, measuring metrics like tokens/second and TCO, while modeling competitor pricing to inform sales strategies. Requires 5+ years in ML systems and deep expertise in open-source inference stacks and transformer optimizations.
Leads new ML research team focusing on post-training/RL, dataset optimization, LLM pretraining, sparsity, and domain-specific agents. Adapts algorithms for Cerebras hardware, builds teams, and collaborates on hardware/software design. Requires PhD and ML leadership experience.
Designs and implements AI/ML and scientific computing workloads on wafer-scale hardware to set performance benchmarks. Leads algorithm-hardware co-design, builds performance models, and contributes to technology roadmap with publications in top venues. PhD preferred in CS, Engineering, or related field.
Build and optimize scalable machine learning systems for LLM pretraining, fine-tuning, alignment, and evaluation. The role requires 4+ years of ML systems experience, strong Python and PyTorch skills, and familiarity with transformers; experience with LLMs, reinforcement learning, and distributed training is preferred.
Build system-level debugging, validation, observability, and anomaly-analysis tooling for Cerebras’s AI hardware and software stack. The role requires strong C++ and Python skills, experience debugging complex hardware/software systems, and familiarity with compilers, runtimes, or high-performance computing.
Build and optimize Cerebras’s production GPU prefill and inference stack across APIs, serving runtimes, ROCm, distributed systems, and hardware. The role requires 5+ years of software engineering experience, strong C++ and Python skills, and hands-on experience operating high-performance model-serving systems.
Build and optimize Cerebras’s production GPU inference stack across APIs, vLLM, PyTorch, ROCm, distributed systems, and AMD infrastructure. The role requires 8+ years of software engineering experience, strong C++ and Python skills, and deep expertise in GPU performance, reliability, and model serving.
Characterize, analyze, and optimize performance of state-of-the-art AI models on Cerebras' wafer-scale hardware. Build performance models, optimize kernels and compilers, debug runtime behavior, and develop visualization tools to influence next-gen AI architecture.
Own model quality and performance for Cerebras inference by building AI agent-driven eval suites, automating benchmarking, and creating customer-specific tooling. Requires strong AI agent experience and tooling intuition.
Senior Performance Engineer benchmarks Cerebras inference performance against competitors for real workloads, measuring metrics like tokens/second and TCO, while modeling competitor pricing to inform sales strategies. Requires 5+ years in ML systems and deep expertise in open-source inference stacks and transformer optimizations.
Leads new ML research team focusing on post-training/RL, dataset optimization, LLM pretraining, sparsity, and domain-specific agents. Adapts algorithms for Cerebras hardware, builds teams, and collaborates on hardware/software design. Requires PhD and ML leadership experience.
Designs and implements AI/ML and scientific computing workloads on wafer-scale hardware to set performance benchmarks. Leads algorithm-hardware co-design, builds performance models, and contributes to technology roadmap with publications in top venues. PhD preferred in CS, Engineering, or related field.
Build and optimize scalable machine learning systems for LLM pretraining, fine-tuning, alignment, and evaluation. The role requires 4+ years of ML systems experience, strong Python and PyTorch skills, and familiarity with transformers; experience with LLMs, reinforcement learning, and distributed training is preferred.
Build system-level debugging, validation, observability, and anomaly-analysis tooling for Cerebras’s AI hardware and software stack. The role requires strong C++ and Python skills, experience debugging complex hardware/software systems, and familiarity with compilers, runtimes, or high-performance computing.
Get a push summary when new jobs match your saved alerts.
Build and optimize Cerebras’s production GPU prefill and inference stack across APIs, serving runtimes, ROCm, distributed systems, and hardware. The role requires 5+ years of software engineering experience, strong C++ and Python skills, and hands-on experience operating high-performance model-serving systems.