Search
Go
AI Runtime Engineer
Summary by AIEngineer.careers
AI Runtime Engineer is a AI Runtime Engineer role (full-time). with Modular Inc. in CITY OF EDINBURGH, GB. Compensation shown: $110K–$165K (est.). Imported listing (source: aihackerjobs.com). Apply on the employer's site (aihackerjobs.com).
Imported listing (source: aihackerjobs.com) · Apply on aihackerjobs.com
CITY OF EDINBURGH · GB
$110K–$165K (est.)
Full-time
MID
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from aihackerjobs.com
Modular, a Qualcomm company, is seeking an AI Runtime Engineer to own and optimize a runtime that operates across CPU, GPU, and accelerator hardware. You will design cross-stack optimizations, collaborate with compiler and kernel teams, and engage with customers to achieve state-of-the-art performance for AI models.
Responsibilities
- Design and develop runtime and cross-stack optimizations to improve CPU, GPU, and accelerator efficiency.
- Work with vendor-specific networking libraries to enable high-performance data transfer.
- Collaborate with compiler, kernels, serving, and models teams to achieve end-to-end performance.
- Engage with customers to understand performance requirements and use cases.
- Collaborate with tooling and infrastructure teams to design automated performance analysis and benchmarking systems.
Requirements
- 2+ years of experience in high-performance computing systems.
- Proficiency in C++ and complex software systems.
- Experience with CPU or GPU runtime optimizations and performance analysis.
- Familiarity with profiling tools for CPU or GPU.
- Strong problem-solving skills and team-oriented attitude.
Modular Inc
Los Altos · US · 378+ employees
Modular, Inc. (now Modular, a Qualcomm company) develops AI infrastructure software. Its platform, including Modular Accelerated Xecution (MAX) and Mojo, is designed to improve the performance, portability, and programmability of AI workloads, including production inference.
