Staff Engineer, Inference Optimizations

Role Description

DigitalOcean is seeking a Senior Engineer 2 to play a key technical role in our AI Inference Optimization team. You will help ensure we can offer industry-leading performance for our inference services.

• Performance Architecture: Lead the technical strategy for benchmarking and performance optimizations at the inference engine and GPU kernel layers.
• Deep-Dive Optimization: Engineer solutions for complex performance issues, including attention layer optimizations, memory and precision management, and advanced parallelization across multi-node GPU clusters.
• Technological Innovation: Proactively implement cutting-edge optimization techniques to keep DigitalOcean at the forefront of the Gen AI landscape.
• Hardware & Ecosystem Mastery: Act as the subject matter expert on modern GPU families (NVIDIA/AMD) and their software stacks (CUDA, ROCm, TensorRT, OpenAI Triton).
• Precision Optimization: Develop and deploy state-of-the-art quantization techniques (FP8, INT8, and experimental FP4) to double throughput without losing accuracy.
• Technical Mentorship: Lead by example through high-quality code and design reviews.
• Strategic Collaboration: Partner with Product Management and TPMs to translate "theoretical hardware limits" into "shippable product features."
• Community Leadership: Maintain a strong presence in the GPU infrastructure and model performance optimization communities.

Qualifications

• 5+ years of experience in high-performance computing or AI infrastructure.
• Deep familiarity with the Gen AI (LLM, VLM, LMM) landscape.
• Hands-on experience with attention-layer optimizations and parallelization strategies across distributed GPU environments.
• Comprehensive understanding of NVIDIA and AMD GPU architectures and their respective software ecosystems (CUDA, ROCm, etc.).
• Extensive experience integrating, building with, and contributing to open-source software projects.
• Excellent system design skills, particularly related to low-level GPU programming.
• Experience acting as a technical lead, driving design and delivery through cross-functional alignment.
• Deep understanding of GPU architectures (SMs, Warp scheduling, Tensor Cores).
• Expert-level Triton or CUDA experience.

Requirements

• Proven track record of solving compute utilization and memory bandwidth bottlenecks.
• Experience with attention-layer optimizations and parallelization strategies.
• Expertise in low-level GPU programming and optimization.

Benefits

• Competitive array of benefits including Employee Assistance Program and flexible time off policy.
• Reimbursement for relevant conferences, training, and education.
• Access to LinkedIn Learning's 10,000+ courses for continued growth and development.
• Salary range based on market data, relevant years of experience, and skills.
• Potential for bonus based on company and individual performance.
• Equity compensation to eligible employees, including equity grants and Employee Stock Purchase Program.

Company Description

DigitalOcean is an equal-opportunity employer. We do not discriminate on the basis of race, religion, color, ancestry, national origin, caste, sex, sexual orientation, gender, gender identity or expression, age, disability, medical condition, pregnancy, genetic makeup, marital status, or military service.