Senior AI Inference Optimizations Engineer — Remote

DigitalOcean; Seattle (WA); Remote; USD 167,200 - 209,000; Full time

Benefits offered by this job

Flexible time off

Employee Stock Purchase Program

Career development resources

Job summary

A cloud technology company is looking for a Senior Engineer 2 to enhance their AI Inference Optimization team. In this role, you will drive architectural decisions that improve throughput and reduce latency in large models. Candidates should have over 5 years of experience in high-performance computing, strong leadership capabilities, and deep familiarity with AI infrastructure. This position offers competitive compensation and is fully remote, promoting a collaborative and innovative work environment.

Qualifications

• 5+ years of experience in high‑performance computing or AI infrastructure.
• Deep familiarity with the Gen AI landscape, including major model families.
• Comprehensive understanding of NVIDIA and AMD GPU architectures.

Responsibilities

• Lead the technical strategy for benchmarking and performance optimizations.
• Engineer solutions for complex performance issues in GPU environments.
• Advise on hardware procurement and software integration.

Skills

High-performance computing

AI infrastructure

Attention-layer optimizations

Parallelization strategies

Technical leadership

Tools

CUDA

ROCm

TensorRT

Job description

A cloud technology company is looking for a Senior Engineer 2 to enhance their AI Inference Optimization team. In this role, you will drive architectural decisions that improve throughput and reduce latency in large models. Candidates should have over 5 years of experience in high-performance computing, strong leadership capabilities, and deep familiarity with AI infrastructure. This position offers competitive compensation and is fully remote, promoting a collaborative and innovative work environment.