Senior Director, Inference Products and Optimizations

Dive in and do the best work of your career at DigitalOcean. Journey alongside a strong community of top talent who are relentless in their drive to build the simplest scalable cloud. If you have a growth mindset, naturally like to think big and bold, and are energized by the fast-paced environment of a true industry disruptor, you’ll find your place here. We value winning together—while learning, having fun, and making a profound difference for the dreamers and builders in the world. Our Inference Engine organization is seeking an experienced Senior Director of Engineering to lead a high-performing engineering team building and scaling our Large Language Model (LLM) inference products across the control plane, model optimization, and model architecture layers. This organization sits at the heart of DigitalOcean's mission to bring our signature simplicity to optimized LLM inference. In this role, you will own DigitalOcean's inference product suite — Serverless Inference, Dedicated Inference, Inference Router, Batch Inference, and Multimodal Inference — along with the model optimization and architecture stack that underpins them. You'll be responsible for delivering robust, cost-efficient systems that serve millions of users globally at scale and high performance. ## **What You'll Do:** - **Team Leadership & Development:** Recruit, mentor, and coach engineers on the team, fostering a culture of ownership, technical excellence, and continuous improvement. - **Build Performant and Scalable Inference Products:** Work with Product teams to define and execute on the Product roadmap for all of DigitalOcean’s Inference Products - including Serverless Inference, Dedicated Inference, Inference Router, Batch Inference and Multimodal Inference - **Inference Optimizations and Model Architecture:** Lead the design and evolution of our inference serving stack, driving deep technical strategy across vLLM, SGLang, and LLM-D to optimize throughput, latency, and GPU utilization at scale. Architect the model-serving and optimization layer — spanning quantization, KV-cache management, speculative decoding, and disaggregated serving — to deliver best-in-class performance-per-dollar across our LLM inference products. - **Cross-Functional Partnership:** Collaborate with Product Management, other engineering teams, and key stakeholders to align priorities, manage dependencies, and communicate progress and risks. - **Operational Health:** Ensure the production health, stability, and on-call rotation of all to maintain the customer SLAs. - **Champion Best Practices:** Institutionalize benchmarking frameworks, observability, and auto-tuning capabilities to guide system and infrastructure tuning efforts. Encourage contributions to open-source inference engines to advance our capabilities. ## **Indicators of a Good Fit:** - **Experience:** 10+ years of software engineering experience, with 6+ years in a technical leadership or management role, ideally within Inference Systems or AI/ML systems. - **Technical Depth:** Deep expertise in distributed systems design, modern AI/ML technologies, Kubernetes at scale, and LLM inference, and AI workload orchestration, scheduling, and resource management. Ability to engage in deep technical discussions with your team regarding highly scalable control plane design, inference engines (vLLM, SGLang), and model architectures. Strong understanding of cloud-native multi region architectures, microservices, and distributed systems fundamentals. - **Hardware-Aware Optimization:** Strategic knowledge of GPU architectures (NVIDIA and/or AMD), interconnects (like NVLink), and hardware topology and their direct impact on AI training and inference performance. - **Systems Engineering & Security:** Familiarity with concepts in container runtime internals, system isolation, and security contexts to manage risk in shared infrastructure. - **Observability and SLOs:** Expertise in defining, tracking, and operationalizing deep infrastr…