Skip to main content

SambaNova

Inference Systems Performance Architect

San Jose, California, United States

Location
San Jose, California, United States
Work
Not stated
Employment
Full-time
Level
Lead / staff
Function
Engineering
Pay
$245K – $325K a year
Posted
2 months ago

About the role

The Inference Systems Performance team answers how fast SambaNova's systems can serve large language models and what it takes to get there. We capture real production traffic, benchmark it faithfully, model and simulate configurations that do not exist yet, and profile the…

Many pages were opened from here in the last minute, so the full ad isn’t loaded. It’s on the company’s site. Read it there ↗

Source

Posted by SambaNova on their own hiring page, sambanova.ai. OptiTalent shows it as published; the original is the reference.

View the original ad ↗

More at SambaNova

  • SambaNova · San Jose, California, United States

    Full-timeDirector$230K – $280K a yearOperations

    SambaNova is looking for a Senior Director of Business Operations and New Product Introduction (NPI) to help bring SambaNova's silicon and systems to market through a growing ecosystem of partners. You will work directly with the Chief Corporate Development Officer, and you…

  • SambaNova · Austin, Texas, United States +1

    Full-timeEntry level$131.2K – $196.8K a yearData & AI

    The Machine Learning team builds the model-side techniques that make SambaNova’s platform fast and capable. We train speculative decoding models that accelerate inference, develop efficient ML methods such as quantization, sparsity, and distillation, and build agentic systems…

  • SambaNova · Austin, Texas, United States +1

    Full-timeLead / staffEngineering

    The Place and Route team writes the software that maps dataflow graphs onto SambaNova’s Reconfigurable Dataflow Unit (RDU). Our tools partition each graph, place the pieces on the chip’s compute and memory units, and route the communication between them. The quality of that…

  • SambaNova · Austin, Texas, United States +1

    Full-timeLead / staff$208K – $312K a yearEngineering

    We take frontier open-weight models (dense, mixture-of-experts with hundreds of experts, hybrid Mamba/attention, sliding-window attention, multi-token prediction) from Hugging Face to production serving on SambaNova's RDU dataflow accelerators. That means compiling them,…