Director, Engineering - Inference Serving Engine

Our Inference Engine organization is seeking an experienced Engineering Director to lead a high-performing team of engineers as they design, develop, and scale our Large Language Model (LLM) inference platform across the serving, orchestration, and hosting layers. This team is at the heart of our mission to bring DigitalOcean’s famed simplicity to the world of optimized LLM inference. In this role, you will bridge the gap between product strategy and technical execution, fostering a culture of excellence while delivering robust systems that handle millions of users across the globe.

• Team Leadership & Development: Recruit, mentor, and coach engineers on the team, fostering a culture of ownership, technical excellence, and continuous improvement.
• Execution & Delivery: Own the team's project execution, translating high-level business goals into clear technical roadmaps, measurable milestones, and successful, on-time delivery.
• 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 services owned by the Inference Orchestration team.
• Oversee System Design: In partnership with the technical leads on your team, guide the architecture and implementation of a distributed inference platform optimized for diverse GPU platforms (NVIDIA and AMD). Ensure the platform is performant, scalable, and reliable.
• 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.
• Strategic Architecture & Planning: Define the technical roadmap and oversee the architecture of high-throughput scheduling systems for massive Kubernetes clusters (1,000+ nodes, 10,000+ pods), focusing on scalability techniques like multi-scheduler architectures and batch dispatching.
• Maximize GPU Utilization: Engineer solutions for complex performance issues, including attention layer optimizations, memory and precision management, and advanced parallelization across multi-node GPU clusters. Eliminate GPU waste in multi-tenant environments by implementing fractional GPU allocation, leveraging mechanisms like KAI-Scheduler's Reservation Pods or hard-isolation tools like HAMi, and configuring time-based fairshare scheduling to balance over-quota pool access.
• Orchestrate Complex Inference: Implement and manage disaggregated AI inference pipelines using frameworks like NVIDIA Grove, coordinating multicomponent deployments (e.g., prefill leaders, decode workers, KV routers) with multilevel autoscaling and explicit startup ordering.
• Optimize Placement & Topology: Deploy topology-aware scheduling to align pod placement with physical hardware dimensions, such as NVLink connections, PCIe lanes, and NUMA nodes, minimizing communication latency for multi-GPU operations.
• Platform Performance & Reliability: Drive initiatives to enhance overall cluster performance, including optimizing scheduling latency, API server load, and implementing fault tolerance mechanisms like Checkpoint/Restore for long-running AI training jobs.
• Manage AI Storage & Fault Tolerance: Orchestrate efficient model weight distribution using OCI Image Volumes and implement Checkpoint/Restore capabilities (via CRIU and NVIDIA cuda-checkpoint) for long-running training fault recovery.
• Security and Isolation: Define and enforce security best practices for AI workloads, ensuring multi-layered isolation environments and agent sandboxes are deployed to safely execute untrusted code (e.g., using Kata Containers, gVisor, or microVMs).

• Experience: 10+ years of software engineering experience, with 6+ years in a technical leadership or management role, ideally within AI/ML infrastructure or cloud platforms.
• 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 GPU programming (CUDA, ROCm), inference engines (vLLM, SGLang), and infrastructure at scale.
• 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 infrastructure and inference metrics (e.g., TTFT, TPOT) to drive performance improvements and meet service level objectives.
• Product Mindset: Demonstrated ability to translate complex technical requirements into user-focused product features. Understanding of the balance between innovation and reliability.
• Communication: Excellent communication skills, with the ability to explain technical decisions to non-technical stakeholders and align diverse teams around a shared vision.
• Ownership: A strong sense of ownership and a proactive drive to identify and resolve issues preventing your team from delivering value.

*This job is located in Bengaluru, India

#LI-Hybrid