Lead the technical design and implementation of agentic systems and the shared AI platform: model access and routing, agent runtimes, durable orchestration, evaluation, identity, audit, observability, and cost attribution. Role requires substantial architecture experience (typically 10+ years), recent hands-on production experience with LLMs/agents, proficiency in production languages (Python/Go/TypeScript) and cloud-native infrastructure, and experience integrating enterprise systems (Workday, Salesforce, NetSuite, etc.).

DigitalOcean seeks a Staff Engineer (Inference Optimizations) to lead benchmarking and performance work at the inference engine and GPU-kernel level. Responsibilities include attention-layer and kernel optimizations, memory/precision management, multi-node GPU parallelization, and deploying quantization techniques. Requires 5+ years in HPC or AI infrastructure and deep experience with NVIDIA/AMD GPUs, CUDA/ROCm, Triton/CUDA kernels. Compensation range $191,200–$239,000/year.

DigitalOcean seeks a Staff Engineer to lead architectural and low-level performance work for AI inference: benchmarking, GPU kernel optimization, attention-layer and memory/precision management, kernel fusion, quantization (FP8/INT8/FP4), and multi-node GPU parallelization. Requires deep GPU hardware/software expertise (NVIDIA/AMD, CUDA, ROCm, Triton) and 5+ years in high-performance computing or AI infrastructure.

Lead technical work on benchmarking and optimizing inference engines and GPU kernels to maximize throughput and minimize latency for large models. Responsibilities include attention-layer and memory optimizations, quantization (FP8/INT8/FP4), kernel fusion, multi-node GPU parallelization, and advising on GPU hardware/software stacks (CUDA, ROCm, Triton). Requires 5+ years in high-performance computing or AI infrastructure. Salary range provided.

DigitalOcean is hiring a staff/senior engineer to drive architectural decisions and implement performance optimizations at the inference engine and GPU kernel layers. Responsibilities include attention-layer and kernel optimizations, quantization (FP8/INT8/FP4), multi-node GPU parallelization, and benchmarking across NVIDIA and AMD stacks (CUDA, ROCm, Triton). Requires 5+ years in high-performance computing or AI infrastructure and deep GPU/low-level optimization experience.

Senior Solutions Architect II focused on cloud infrastructure and AI/ML who will work with Sales, Customer Success, and Engineering to retain and grow large customers. Responsibilities include architecture reviews, POCs, LLM and GenAI deployment and optimization (TensorFlow, PyTorch, Hugging Face, CUDA/TensorRT), Kubernetes-based solutions, infrastructure best practices, cost and performance optimization, and delivering technical workshops and documentation. Fluency in English required.

Technical lead responsible for architecting, building, and operating Kubernetes-native distributed inference hosting (prefill/decode disaggregation, KV-cache-aware routing, tiered caching, MoE support). Requires experience with LLM inference frameworks (vLLM, llm-d, Ray Serve, NVIDIA Dynamo), Go or Python, gRPC, observability and SLOs, performance optimization, and contributing to open-source inference projects.