Staff GPU Inference Engineer - High-Performance AI

FDE Times

Toronto

On-site

CAD 251,000 - 335,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Cerebras Systems is hiring a Software Engineer to productionize and optimize our GPU serving stack. You will work across custom inference APIs, vLLM, PyTorch, ROCm, and rack-scale AMD GPU infrastructure to ensure reliability, numerical correctness, observability, and high performance.

You will write production-grade code, establish operational practices for a new accelerator fleet, and drive improvements in latency, throughput, and capacity.

Qualifications

  • Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or related field.
  • Experience with production-grade inference systems for large language or multimodal models.
  • Strong programming skills in C++ and Python with performance sensitivity.

Responsibilities

  • Productionize GPU inference stack across API services and model-serving workers.
  • Own deployment, upgrade, health checks, and capacity management for the AMD GPU fleet.
  • Improve time to first token, throughput, tail latency, and capacity efficiency.
  • Tune scheduling, batching, KV-cache, and memory management for efficient inference.
  • Diagnose failures across application, runtime, and hardware layers.

Skills

C++ programming
Python programming
multithreading
performance optimization
distributed systems
debugging complex systems
Linux
CI/CD
communication

Education

Bachelor’s degree in CS/CE or related

Tools

vLLM
PyTorch
ROCm
HIP
Triton Inference Server
SGLang
TensorRT-LLM

Job description

Cerebras Systems is hiring a Software Engineer to productionize and optimize our GPU serving stack. You will work across custom inference APIs, vLLM, PyTorch, ROCm, and rack-scale AMD GPU infrastructure to ensure reliability, numerical correctness, observability, and high performance.

You will write production-grade code, establish operational practices for a new accelerator fleet, and drive improvements in latency, throughput, and capacity.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Software Engineer, GPU Inference
Software Engineer, GPU Inference

Cerebras • Toronto

On-site
CAD 140,000 - 210,000
Staff Software Engineer, GPU Inference
Staff Software Engineer, GPU Inference

Cerebras • Toronto

On-site
CAD 150,000 - 210,000
Staff Software Engineer, GPU Inference
Staff Software Engineer, GPU Inference

FDE Times • Toronto

On-site
CAD 251,000 - 335,000
Senior Software Engineer, ML API - AI Inference
Senior Software Engineer, ML API - AI Inference

Cerebras • Toronto

On-site
CAD 130,000 - 190,000
Remote-friendly? (not stated)
Staff Software Engineer, AI Inference Systems
Staff Software Engineer, AI Inference Systems

Cerebras • Toronto

On-site
CAD 140,000 - 190,000
Staff Software Engineer, Inference API
Staff Software Engineer, Inference API

Cerebras • Toronto

On-site
CAD 140,000 - 190,000
Software Engineer, Inference Platform
Software Engineer, Inference Platform

Cerebras • Toronto

On-site
CAD 256,000 - 370,000
CoDesign & NextGen Performance Engineer
CoDesign & NextGen Performance Engineer

Cerebras • Toronto

On-site
CAD 110,000 - 170,000
Senior AI Systems Engineer: GPU Training & Inference
Senior AI Systems Engineer: GPU Training & Inference

Advanced Micro Devices, Inc. • Markham

On-site
CAD 140,000 - 190,000
Staff Software Engineer, Inference Platform
Staff Software Engineer, Inference Platform

Cerebras • Toronto

On-site
CAD 293,000 - 405,000