← All roles

ML Research Scientist - Inference ML

Cerebras· Software Engineering
Apply on company site
United States and CanadaFull-timePosted 3w ago

About the role

ML Research Scientist focusing on inference methods and model architectures to enable low-latency, high-throughput inference on Cerebras hardware. Role emphasizes speculative decoding, pruning/compression, sparse attention, and sparsity-driven techniques, working across research and engineering to translate findings into production-ready systems.

Responsibilities

  • Research and prototype novel inference algorithms and model architectures that exploit Cerebras hardware, with emphasis on speculative decoding, pruning/compression, sparse attention, and sparsity.
  • Design and evaluate new transformer architectures and variants for NLP and computer vision to improve quality, latency, throughput, and compute.
  • Identify and pursue high-impact research directions at the intersection of model architecture, inference systems and hardware.
  • Train or adapt models where needed, and measure and analyze inference performance using Cerebras tools to maximize throughput and minimize latency.
  • Collaborate with engineering and performance teams to translate research into usable systems from inception through delivery.
  • Publish and present research findings and contribute to open-source releases where appropriate.

Qualifications

  • PhD in machine learning, computer science, or a closely related technical field with 3+ years of relevant research or industry experience, OR a master’s degree with an exceptional record of original, independent research and 4+ years of relevant experience.
  • Deep understanding of modern ML architectures and generative models in language and/or vision domains, machine learning systems, and inference principles.
  • Ability to reason about model and algorithm performance for inference workloads.
  • Ability to identify practically relevant research questions, develop novel methods, and evaluate effects on model quality and inference efficiency.
  • Evidence of research impact through publications, high-quality preprints, or widely used open-source contributions.
  • Strong Python programming skills and proficiency with ML frameworks such as PyTorch, Transformers, vLLM, or SGLang.

Skills

Required:Inference algorithm researchTransformer architecturesPerformance analysisPython programmingML frameworks (PyTorch, Transformers, vLLM, SGLang)

Benefits

  • Not specified in the description
Last updated Oct 11, 2026. Interested? Apply on the company site.

About Cerebras

Cerebras is the go-to platform for fast and effortless AI training. Learn more at cerebras.ai.

Cerebras is the go-to platform for fast and effortless AI training.

AICerebras Wafer-Scale Enginechipshardwareinferenceliquid-ai-recruiting-targetmultimodalsetter-30
Company profileWebsite

More open roles at Cerebras