Senior Engineer 2: Inference Optimizations

📋 Description

• Lead benchmarking and performance optimizations for inference engines and GPU kernels.
• Deep-dive into attention/memory/precision optimization and multi-node GPUs.
• Proactively implement cutting-edge optimization techniques for Gen AI workloads.
• Master GPU hardware and software stacks (CUDA, ROCm, TensorRT, Triton).
• Mentor through code and design reviews to raise the team's bar.
• Collaborate with Product/TPMs to translate hardware limits into features.

🎯 Requirements

• 5+ years in high-performance computing or AI infrastructure.
• Gen AI literacy across LLM, VLM, and LMM architectures.
• Optimization expert in attention layers and distributed GPU parallelism.
• Hardware fluency with NVIDIA/AMD GPUs; CUDA/ROCm ecosystems.
• Open source experience: build, integrate, contribute.
• Strong systems design for low-level GPU programming and memory access.

🎁 Benefits

• Reimbursement for conferences, training, and education.
• LinkedIn Learning access to 10,000+ courses.
• EAP and local employee meetups; flexible time off.
• Salary range based on market data; potential bonus.
• Equity grants and Employee Stock Purchase Program.
• DigitalOcean is an equal-opportunity employer.