About the job
Tenstorrent is at the forefront of groundbreaking AI technology, setting new benchmarks for performance, usability, and cost-effectiveness. As AI reshapes the computing landscape, our solutions are designed to integrate advancements in software models, compilers, platforms, networking, and semiconductors. Our talented team has crafted a high-performance RISC-V CPU from the ground up and is united by a shared enthusiasm for AI and a commitment to creating the premier AI platform. We cherish collaboration, curiosity, and a relentless drive to tackle complex challenges. We are expanding our team and are on the lookout for contributors at all experience levels.
Become a part of our Inference Server Technologies team, where we create software that drives cutting-edge AI inferencing on Tenstorrent’s innovative hardware. Our team focuses on building the layer that operates on top of Tenstorrent's ML libraries—designing APIs, deploying workloads, and benchmarking end-to-end inference speed. You will play a crucial role in shaping how developers engage with and scale model execution on Tenstorrent’s infrastructure.
This role is hybrid based in Belgrade, Serbia.
We encourage candidates of all experience levels to apply. During the interview process, we will evaluate candidates for the appropriate level, and offers will be tailored accordingly.

