ML Research Engineer (Inference)

Role Overview: You will be a Research Engineer on the Inference ML team at Cerebras Systems, where you will be responsible for adapting advanced language and vision models to efficiently run on the flagship Cerebras architecture. Working closely with ML researchers and engineers, you will design, prototype, validate, and optimize models to push the boundaries of inference research on the world's fastest AI accelerator. Key Responsibilities: - Implement and adapt transformer-based models (NLP and/or vision) to operate on Cerebras hardware - Assist in optimizing models for inference performance, focusing on latency and throughput - Conduct experiments, analyze outcomes, and contribute to model enhancements - Assist in setting up and validating models on the Cerebras system - Troubleshoot and debug model or system issues under the guidance of senior team members - Support profiling and performance analysis utilizing internal tools - Collaborate with cross-functional teams (ML, software, hardware) for model integration Qualifications Required: - Bachelors or Masters degree in Computer Science, Engineering, or a related field - 13 years of experience in software engineering or machine learning, including internships - Proficiency in Python and at least one ML framework (e.g., PyTorch, Transformers, vLLM or SGLang) - Understanding of deep learning concepts such as neural networks and transformers - Experience with Generative AI and Machine Learning systems - Strong programming skills in Python and/or C++ Additional Details: Cerebras Systems is known for building the world's largest AI chip, 56 times larger than GPUs. Their wafer-scale architecture provides significant AI compute power on a single chip, simplifying programming and delivering industry-leading training and inference speeds. Cerebras' collaboration with OpenAI and their commitment to groundbreaking technology make it an exciting place to work and contribute to cutting-edge advancements in the AI industry. If you are passionate about AI research and want to work on cutting-edge technology that is revolutionizing the industry, Cerebras Systems offers a unique opportunity to be part of a dynamic team that values innovation and collaboration. Apply now and be at the forefront of groundbreaking advancements in AI! Role Overview: You will be a Research Engineer on the Inference ML team at Cerebras Systems, where you will be responsible for adapting advanced language and vision models to efficiently run on the flagship Cerebras architecture. Working closely with ML researchers and engineers, you will design, prototype, validate, and optimize models to push the boundaries of inference research on the world's fastest AI accelerator. Key Responsibilities: - Implement and adapt transformer-based models (NLP and/or vision) to operate on Cerebras hardware - Assist in optimizing models for inference performance, focusing on latency and throughput - Conduct experiments, analyze outcomes, and contribute to model enhancements - Assist in setting up and validating models on the Cerebras system - Troubleshoot and debug model or system issues under the guidance of senior team members - Support profiling and performance analysis utilizing internal tools - Collaborate with cross-functional teams (ML, software, hardware) for model integration Qualifications Required: - Bachelors or Masters degree in Computer Science, Engineering, or a related field - 13 years of experience in software engineering or machine learning, including internships - Proficiency in Python and at least one ML framework (e.g., PyTorch, Transformers, vLLM or SGLang) - Understanding of deep learning concepts such as neural networks and transformers - Experience with Generative AI and Machine Learning systems - Strong programming skills in Python and/or C++ Additional Details: Cerebras Systems is known for building the world's largest AI chip, 56 times larger than GPUs. Their wafer-scale architecture provides significant AI compute power on a single chip, simplifying programming and delivering industry-leading training and inference speeds. Cerebras' collaboration with OpenAI and their commitment to groundbreaking technology make it an exciting place to work and contribute to cutting-edge advancements in the AI industry. If you are passionate about AI research and want to work on cutting-edge technology that is revolutionizing the industry, Cerebras Systems offers a unique opportunity to be part of a dynamic team that values innovation and collaboration. Apply now and be at the forefront of groundbreaking advancements in AI!