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.

Responsible for defining DigitalOcean's reference architectures for next-generation data center environments (air to liquid to 800VDC rack-scale), leading MEP coordination for colocation and build-to-suit sites, architecting cooling and power topologies, driving PoCs to global standards, and mentoring engineers. Requires 10+ years in data center architecture/infrastructure; compensation listed as $184,000–$231,000/year.

Principal Datacenter Architect responsible for defining reference architectures for next-generation data centers (air to liquid to 800VDC rack-scale), owning MEP requirements across colocation and build-to-suit facilities, leading PoCs and vendor integrations, guiding site selection and non-traditional infrastructure approaches, and mentoring engineers. Requires 10+ years experience. This is a hybrid role based in Seattle.

Hands-on senior engineer responsible for architecting and implementing high-availability, low-latency IAM services in Go; building OIDC/SAML SSO integrations; evolving a policy engine (Rego/OPA) for advanced permissions; operating Kubernetes deployments and modern eventing pipelines; and mentoring junior engineers. Requires 5+ years of software engineering experience and strong identity, distributed systems, and cloud-native expertise.

Senior Software Engineer (IC3) responsible for designing and developing high-availability, low-latency authentication and authorization services in Go; implementing OIDC/SAML SSO integrations; evolving a policy engine (Rego/OPA) for advanced authorization; operating services on Kubernetes; and mentoring engineers. Requires 5+ years software engineering experience and strong identity, distributed systems, and cloud-native skills. Role is listed as remote.

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 leader role on DigitalOcean's AI Inference Data Plane team building Kubernetes-native, distributed inference hosting for large language and multimodal models. Responsibilities include system design, performance optimization (KV-cache, tensor/data parallelism), building on frameworks like llm-d/vLLM/Ray Serve, operating high-scale services with observability and SLOs, and contributing upstream to open-source projects. Strong experience with Go or Python, gRPC, and inference engines (vLLM, TensorRT, SGLang, etc.) is required.

Hands-on technical leader responsible for designing, developing, optimizing, and operating distributed inference hosting and data-plane components to support large generative AI models. Work includes system architecture, performance tuning (tensor/data parallelism, KV cache, batching, quantization), GPU/interconnect optimization, cross-functional collaboration, mentoring, and maintaining observability and SLOs. Primary languages/tools: Go or Python, gRPC, and various inference frameworks (vLLM, llm-d, NVIDIA Dynamo, Ray Serve).

Technical lead on the AI Inference Engine team responsible for end-to-end design, development, and operation of a multi-tenant inference hosting platform. Role focuses on distributed systems design, performance optimization (tensor/data parallelism, KV cache, quantization), GPU/interconnect optimizations (NVLink, XGMI, RoCE), and mentoring engineers. Requires experience with inference frameworks (vLLM, llm-d, Ray Serve), microservices and cloud operations, and proficiency in Go or Python and gRPC.