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.

Features

Auto Apply Resume Optimizer Cover Letter Optimizer Interview Prep

Company

Social Media

Need Help?

team@applyblast.com

ML Systems Performance Engineer at Cerebras Systems - ApplyBlast

ML Systems Performance Engineer

Cerebras Systems

4 months ago

India

Onsite

Full Time

Senior

0 applicants

View Job Listing

Apply to 100+ jobs

About this role

Engineers on the inference performance team at Cerebras Systems operate at the intersection of hardware and software to drive end-to-end model inference speed and throughput. The role involves building performance models, optimizing kernel micro-code and compiler algorithms, debugging runtime performance, and developing diagnostic tooling for the Wafer Scale Engine.

Responsibilities

Build performance models to estimate ML model inference speed and throughput
Optimize and debug kernel micro-code and compiler algorithms for the WSE
Debug and analyze runtime performance on the system and compute cluster
Develop tools and infrastructure to visualize performance data
Collaborate with model labs and enterprises to deliver high-speed inference

Skills

Qualifications

Bachelors in Electrical EngineeringMasters in Computer SciencePhD in Electrical EngineeringPhD in Computer Science

About Cerebras Systems

cerebras.ai

Headquarters

Sunnyvale, California, United States

Company Size

201-500 employees

Founded

2015

View Profile

Cerebras is an AI compute company powering the world's fastest AI inference through its proprietary Wafer-Scale Engine chip, which is purpose-built for ultra-fast AI and 58x larger than GPUs. The company offers cloud, dedicated, and on-premises deployment options, enabling developers and enterprises to serve, fine-tune, and pre-train large models at speeds up to 15x faster than GPU-based systems. Cerebras serves a broad range of customers—from leading AI labs like OpenAI to enterprises in healthcare, finance, and software—through a developer-friendly API with drop-in OpenAI compatibility.