Senior AI Inference Optimization Engineer (Remote)

DigitalOcean; United States; Remote; USD 191,000 - 239,000; Full time

Job summary

DigitalOcean is seeking a Senior Engineer 2 in AI Inference Optimization to drive performance across inference engines and GPU kernels. You will lead optimization efforts, collaborate with product teams, and push the frontier of Gen AI efficiencies in a remote setting.

You will influence hardware choices, implement advanced quantization, and mentor engineers while delivering scalable, low-latency inference for cutting-edge large models.

Qualifications

• 5+ years of experience in high-performance computing or AI infrastructure.
• Gen AI literacy with experience in LLM/VLM/LMM landscape.
• Hands-on experience with attention-layer optimizations and distributed GPU parallelization.
• Comprehensive understanding of NVIDIA and AMD GPU architectures and software ecosystems.
• Open source software integration, building, and contributions.

Responsibilities

• Lead the technical strategy for benchmarking and performance optimizations at the inference engine and GPU kernel layers.
• Engineer solutions for complex performance issues including attention optimizations and memory/precision management.
• Implement cutting-edge optimization techniques to keep DigitalOcean at the forefront of Gen AI.
• Advise on hardware procurement and software integration for GPUs.
• Develop and deploy quantization techniques (FP8, INT8, FP4) to boost throughput.
• Provide technical mentorship and lead by example in design reviews.
• Collaborate with Product Management to translate hardware limits into product features.
• Maintain community leadership in GPU performance optimization.

Skills

High-performance computing

AI infrastructure

GPU architectures

CUDA / ROCm

Open Source

Leadership through influence

Tools

Triton

CUDA

ROCm

TensorRT

Job description

DigitalOcean is seeking a Senior Engineer 2 in AI Inference Optimization to drive performance across inference engines and GPU kernels. You will lead optimization efforts, collaborate with product teams, and push the frontier of Gen AI efficiencies in a remote setting.

You will influence hardware choices, implement advanced quantization, and mentor engineers while delivering scalable, low-latency inference for cutting-edge large models.