Elevate AI innovation with Cerebras Systems as a Senior Research Engineer focusing on Inference ML. Collaborate with leading experts to enhance language and vision models on our powerful AI architecture.In this pivotal role, you will drive advancements in machine learning by adapting cutting-edge models for optimal performance on Cerebras' unique hardware. You will work with ML researchers to innovate inference techniques such as speculative decoding and large-model pruning to achieve low-latency, high-throughput outcomes at scale. Your contributions will have significant implications for AI applications worldwide.Key Responsibilities:
Design and optimize transformer architectures for NLP and computer vision
Prototype novel inference algorithms leveraging Cerebras' capabilities




Train models to convergence and analyze performance metrics
Validate functional correctness of current models on Cerebras systems
Optimize model code for maximum throughput and minimal latencyRequirements:
4+ years in software product testing or 3+ years in machine learning
Robust programming skills in Python and/or C++
Experience with Generative AI systems
Evidence of research impact through publications
Familiarity with ML frameworks like Py Torch or TransformersShape the future of AI by enhancing model performance and user experience at Cerebras.#J-18808-Ljbffr

📌 Senior Research Engineer Inference Ml At Cerebras Toronto
🏢 Cerebras Systems
📍 Toronto