ApplyBlast uses AI to match you with the right jobs, tailor your resume and cover letter, and apply automatically so you can land your dream job faster.
© All Rights Reserved. ApplyBlast.com
ApplyBlast uses AI to match you with the right jobs, tailor your resume and cover letter, and apply automatically so you can land your dream job faster.
© All Rights Reserved. ApplyBlast.com
Inferact
The company is seeking a TPU and AMD GPU performance engineer to optimize vLLM as a first-class inference engine for non-NVIDIA hardware. The role involves building, optimizing, and maintaining backend kernels, compiler integrations, and benchmarking infrastructure for AMD GPUs and TPUs. This position focuses on improving inference paths like attention and GEMM to enable efficient AI model serving across heterogeneous accelerator platforms.
Inferact is a production AI inference platform built by the creators and maintainers of vLLM, designed to give organizations control over frontier inference workloads. It allows deployment on customers' own GPUs or Inferact's cloud infrastructure, with support for open weight models and optimization for cost, latency, and throughput. Inferact serves AI teams requiring enterprise-grade performance, security, and day-zero support for the latest frontier models.
Headquarters
San Francisco, CA
Company Size
201-500 employees
Founded
2018
Industry
Technology
Glassdoor Rating
4.2 / 5
Sarah Johnson
Chief Executive Officer
Michael Chen
Chief Technology Officer
Emily Williams
VP of Engineering
David Rodriguez
VP of Product
Jessica Thompson
Chief Financial Officer
Andrew Park
VP of Sales
View leadership team, funding history,
and employee contacts for Inferact.
75% above the average for this role