Senior Research Engineer - Inference ML

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services.

This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation.

Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

As a Senior Research Engineer on the Inference ML team at Cerebras Systems, you will adapt today's most advanced language and vision models to run efficiently on our flagship Cerebras architecture. You'll work alongside ML researchers and engineers to design, prototype, validate, and optimize models, gaining end-to-end exposure to cutting-edge inference research on the world's fastest AI accelerator. 

You will focus on pushing the frontier of speculative decoding, large-model pruning and compression, sparse attention, and sparsity-driven techniques to deliver low-latency, high-throughput inference at scale. 

• →

  Design, implement, and optimize state-of-the-art transformer architectures for NLP and computer vision on Cerebras hardware. 

• →

  Research and prototype novel inference algorithms and model architectures that exploit the unique capabilities of Cerebras hardware, with emphasis on speculative decoding, pruning/compression, sparse attention, and sparsity. 

• →

  Train models to convergence, perform hyperparameter sweeps, and analyze results to inform next steps. 

• →

  Bring up new models on the Cerebras system, validate functional correctness, and troubleshoot any integration issues. 

• →

  Profile and optimize model code using Cerebras tools to maximize throughput and minimize latency. 

• →

  Develop diagnostic tooling or scripts to surface performance bottlenecks and guide optimization strategies for inference workloads. 

• →

  Collaborate across teams, including software, hardware, and product, to drive projects from inception through delivery. 

• One of the following education and experience combinations: 

  • Bachelor’s degree in Computer Science, Software Engineering, Computer Engineering, Electrical Engineering, or a related technical field AND 7+ years of ML software development experience, OR 

  • Master’s degree in Computer Science or related technical field AND 4+ years of software development experience, OR 

  • PhD in Computer Science or related technical field with 2+ years of relevant research or industry experience, OR 

  • Equivalent practical experience. 

• • Master’s degree or PhD in Computer Science, Computer Engineering, or a related technical field. 

  • Experience independently driving complex ML or inference projects from prototype to production-quality implementations. 

  • Hands-on experience with relevant ML frameworks such as PyTorch, Transformers, vLLM, or SGLang. 

  • Experience with large language models, mixture-of-experts models, multimodal learning, or AI agents. 

  • Experience with speculative decoding, neural network pruning and compression, sparse attention, quantization, sparsity, post-training techniques, and inference-focused evaluations. 

  • Familiarity with large-scale model training and deployment, including performance and cost trade-offs in production systems. 

  • Triton/CUDA experience is a big plus.

• Proficiency with at least one major ML framework (PyTorch, Transformers, vLLM, or SGLang). 

• Deep understanding of transformer-based models in language and/or vision domains, with demonstrated experience implementing and optimizing them. 

• Proven ability to translate research ideas into robust code: implementing new model variants, training strategies, and evaluation workflows end-to-end.

• Strong foundation in performance optimization on specialized hardware (e.g., GPUs, TPUs, or HPC interconnects). 

• Deep understanding of modern ML architectures and strong intuition for optimizing their performance, particularly for inference workloads using sparse attention, pruning/compression, and speculative decoding. 

• Track record of owning problems end-to-end and autonomously acquiring whatever knowledge is needed to deliver results. 

• Self-directed mindset with a demonstrated ability to identify and tackle the most impactful problems. 

• Collaborative approach with humility, eagerness to help colleagues, and commitment to team success. 

• Genuine passion for AI and a drive to push the limits of inference performance. 

• Hybrid role in Toronto, ON, CA or Sunnyvale, CA, USA.

Cerebras Systems is committed to creating an equal and diverse environment and is proud to be an equal opportunity employer. We celebrate different backgrounds, perspectives, and skills. We believe inclusive teams build better products and companies. We try every day to build a work environment that empowers people to do their best work through continuous learning, growth and support of those around them.

This website or its third-party tools process personal data. For more details, click here to review our CCPA disclosure notice.