Remote Senior AI Inference Optimization Engineer

DigitalOcean; San Francisco (CA); On-site; USD 191,200 - 239,000; Full time

Benefits offered by this job

Equity compensation

Remote work

Job summary

DigitalOcean is seeking a Senior Engineer 2 to drive AI Inference Optimization. You will lead benchmarking and optimizations at the inference engine and GPU kernel levels, and guide the technical roadmap for high-performance inference fleets.

Bring 5+ years of HPC or AI infra experience, deep Gen AI knowledge, and hands-on CUDA/Triton expertise to push throughput and reduce latency across multi-node GPU clusters.

Qualifications

• 5+ years of experience in high-performance computing or AI infrastructure.
• Experience solving compute utilization and memory bandwidth bottlenecks.
• Familiarity with Gen AI (LLM, VLM, LMM) landscape and model families.
• Proficiency in GPU architectures and software ecosystems (CUDA, ROCm, etc.).

Responsibilities

• Lead benchmarking and performance optimizations at the inference engine and GPU kernel layers.
• Engineer solutions for attention layer optimizations and memory/precision management.
• Implement cutting-edge optimization techniques for Gen AI workloads.
• Collaborate with product and TPMs to translate hardware limits into features.
• Mentor through code reviews and design discussions.

Skills

GPU optimization

Gen AI knowledge

CUDA/Triton

Parallel processing

Open source

System design

Leadership by influence

Low-level GPU programming

Tools

CUDA

ROCm

TensorRT

Triton

Job description

DigitalOcean is seeking a Senior Engineer 2 to drive AI Inference Optimization. You will lead benchmarking and optimizations at the inference engine and GPU kernel levels, and guide the technical roadmap for high-performance inference fleets.

Bring 5+ years of HPC or AI infra experience, deep Gen AI knowledge, and hands-on CUDA/Triton expertise to push throughput and reduce latency across multi-node GPU clusters.