GPU Systems Engineer - Scale AI Inference (On-site SF/LA)

Vast.ai Inc.; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Health insurance

Dental

Vision

Life insurance

401(k) match

Equity

Onsite meals

Startup culture

Job summary

Vast.ai Inc. is seeking a systems engineer with HPC or parallel programming experience to help scale AI inference. You will design and optimize GPU kernels and tensor libraries, leveraging CUDA/C++ and related frameworks to push the bleeding edge of AI performance.

This role is based on-site in San Francisco or Los Angeles, with a strong emphasis on HPC techniques and scalable workloads. You will collaborate with technical leadership, evaluate architectures, and contribute to improving GPU

Qualifications

• Advanced C++ skills with modern standards (C++17/20).
• Experience with at least one parallel framework (CUDA, HIP, SYCL, OpenCL, OpenACC).
• Strong background in systems optimization and HPC performance tooling.

Responsibilities

• Design and optimize GPU kernels and tensor libraries.
• Translate HPC techniques into scalable AI inference solutions.
• Evaluate emerging architectures and resource management approaches.
• Collaborate with leadership to improve GPU infrastructure efficiency.

Skills

CUDA/C++

GPGPU

Python

Linux

Advanced C++ (C++17/20)

Parallel frameworks (CUDA, HIP, SYCL, 

Job description

Vast.ai Inc. is seeking a systems engineer with HPC or parallel programming experience to help scale AI inference. You will design and optimize GPU kernels and tensor libraries, leveraging CUDA/C++ and related frameworks to push the bleeding edge of AI performance.

This role is based on-site in San Francisco or Los Angeles, with a strong emphasis on HPC techniques and scalable workloads. You will collaborate with technical leadership, evaluate architectures, and contribute to improving GPU