Senior AI Inference Performance Engineer (Remote)

DigitalOcean

San Francisco (CA)

Remote

USD 167,200 - 209,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Competitive salary
Flexible time off policy
Employee Assistance Program
Reimbursement for conferences and education
Access to LinkedIn Learning courses

Job summary

A leading cloud infrastructure company is seeking a Senior Engineer 2 to join their AI Inference Optimization team. The role involves leading the technical strategy for performance architecture and addressing complex performance issues ensuring industry-leading service. Successful candidates will have over 5 years of experience in high-performance computing and a strong understanding of GPU architectures. The position offers a competitive salary range along with remote work flexibility and numerous professional development benefits.

Qualifications

  • 5+ years of experience in high-performance computing or AI infrastructure.
  • Familiar with Gen AI (LLM, VLM, LMM) models and their requirements.
  • Hands-on experience with performance optimizations in distributed GPU environments.
  • Keen understanding of memory bandwidth and compute utilization bottlenecks.

Responsibilities

  • Lead technical strategy for performance optimizations in inference engine.
  • Engineer solutions for complex performance issues related to deep learning.
  • Implement cutting-edge optimization techniques for AI models.
  • Advise on hardware procurement and software integration for GPU.
  • Mentor team through code reviews and design processes.
  • Collaborate with Product Management to translate hardware limits into features.
  • Maintain presence in AI and GPU optimization communities.

Skills

High-performance computing
AI infrastructure
Attention-layer optimizations
Parallelization strategies
NVIDIA GPU architecture
AMD GPU architecture
Open-source software
System design

Tools

CUDA
ROCm
TensorRT
OpenAI Triton

Job description

A leading cloud infrastructure company is seeking a Senior Engineer 2 to join their AI Inference Optimization team. The role involves leading the technical strategy for performance architecture and addressing complex performance issues ensuring industry-leading service. Successful candidates will have over 5 years of experience in high-performance computing and a strong understanding of GPU architectures. The position offers a competitive salary range along with remote work flexibility and numerous professional development benefits.
Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Senior AI Inference Optimizations Engineer — Remote
Senior AI Inference Optimizations Engineer — Remote

DigitalOcean • Seattle (WA)

Remote
USD 167,000 - 209,000
Senior AI Inference Performance Architect
Senior AI Inference Performance Architect

NVIDIA • California (MO)

On-site
USD 152,000 - 242,000
Senior AI Performance Engineer — Remote
Senior AI Performance Engineer — Remote

OpenAI • Los Angeles (CA)

On-site
USD 130,000 - 180,000
Senior AI Infrastructure Performance Engineer
Senior AI Infrastructure Performance Engineer

Crusoe • San Francisco (CA)

On-site
USD 172,000 - 210,000
Senior AI Systems Performance Engineer
Senior AI Systems Performance Engineer

NVIDIA • Town of Texas (WI)

On-site
USD 184,000 - 288,000
GPU Performance Engineer: Scale AI Inference
GPU Performance Engineer: Scale AI Inference

Anthropic • San Francisco (CA)

On-site
USD 315,000 - 560,000
Competitive salary
Equity opportunities
Flexible working hours
+1
Senior AI Inference Data Plane Engineer (Remote)
Senior AI Inference Data Plane Engineer (Remote)

DigitalOcean • Seattle (WA)

Remote
USD 167,000 - 209,000
Senior Inference Performance Engineer - GPU & CUDA
Senior Inference Performance Engineer - GPU & CUDA

inference.net • San Francisco (CA)

Hybrid
USD 220,000 - 320,000
Senior AI Inference Performance Architect | Equity Options
Senior AI Inference Performance Architect | Equity Options

NVIDIA Corporation • California (MO)

Hybrid
USD 152,000 - 241,500
Senior AI Systems Performance Engineer: Drive SOTA Inference
Senior AI Systems Performance Engineer: Drive SOTA Inference

SambaNova • Palo Alto (CA)

On-site
USD 120,000 - 150,000
95% premium coverage for employee medical insurance
Health Savings Account with employer contribution
Flexible Spending Account options