ML Algorithm Mapping and Performance Engineer, Core ML
Cerebras · Sunnyvale, CA
About this role
## About the Role The Core ML team develops novel algorithms for efficient large-scale training and inference. We’re looking for an engineer who can determine how these algorithms should be mapped to the Cerebras architecture, when they outperform competing approaches, and how their advantages change as models, workloads, and hardware systems scale. You’ll combine analytical performance modeling, empirical benchmarking, and hands-on prototyping to characterize the efficiency frontiers of emerging ML algorithms—spanning kernel-level and end-to-end performance. Your work will help the team reason about trade-offs among **model quality, latency, throughput, memory, communication, and compute utilization**. This role will directly influence which research ideas Core ML pursues, how those ideas are implemented on current Cerebras systems, and which capabilities should be considered in future generations of hardware and software. --- ## Responsibilities - Build analytical and empirical performance models for state-of-the-art ML training and inference algorithms. - Characterize asymptotic behavior and identify how algorithmic trade-offs change with **model size, sequence length, batch size, parallelism, and hardware scale**. - Construct **Pareto frontiers** across model quality, latency, throughput, memory footprint, communication, and compute cost. - Develop prototype implementations and benchmarks for the **Cerebras WSE** and relevant GPU/software baselines. - Analyze system behavior to identify kernel, compiler, runtime, communication, and algorithmic bottlenecks. - Evaluate emerging techniques including **parallel token generation, diffusion & speculative decoding, attention, sparsity, mixture-of-experts, low-precision computation, and distributed training**. - Partner with researchers and kernel/compiler/runtime/inference/architecture teams to recommend high-value implementation and co-design directions. - Develop tools and visualizations that make performance projections, measurements, and design trade-offs understandable across engineering and research teams. - Communicate conclusions, assumptions, limitations, and recommendations through technical reports, presentations, and design reviews. --- ## Skills & Qualifications - Bachelor’s, Master’s, PhD, or equivalent practical experience in **Computer Science, Computer Engineering, Electrical Engineering, Mathematics, or a related field**. - Strong foundation in **computer architecture, parallel computing, and systems performance**. - Strong understanding of **machine learning fundamentals** and **ML systems**, including how model/algorithm choices affect compute, memory, communication, accuracy, and scaling. - Experience with analytical performance modeling, algorithmic complexity analysis, benchmarking, or system simulation. - Strong analytical and problem-solving skills; ability to reason from first principles about compute, memory, and communication costs. - Proficiency in **Python** and comfort with **C++**. - Experience profiling and debugging performance in an **ML, HPC, CPU, GPU, or accelerator-based** system. - Ability to move between mathematical analysis, experimental validation, and practical engineering recommendations. --- ## Preferred Skills & Qualifications - Experience with **roofline analysis**, CPU/GPU simulators, kernel optimization, or hardware-software co-design. - Familiarity with **CUDA, Triton, PyTorch, JAX**, or open-source LLM training/inference systems.
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.