Director, Engineering - Inference Serving Engine

📋 Description

• Lead and develop engineers; foster ownership and technical excellence.
• Own project execution; translate goals into roadmaps and milestones.
• Collaborate with Product, other teams, and stakeholders to align priorities.
• Ensure production health, stability, and on-call rotation for owned services.
• Guide architecture of a distributed inference platform across GPUs.

🎯 Requirements

• 10+ years software engineering; 6+ years in leadership roles.
• Distributed systems design; Kubernetes at scale; LLM inference.
• GPU hardware: NVIDIA/AMD, NVLink interconnects, topology.
• AI workloads, scheduling, and resource management at scale.
• Observability and SLOs; deep infra and inference metrics.
• Product mindset; translate tech needs into features; strong ownership.
• Excellent communication; align diverse teams.

🎁 Benefits

• Career development resources, conferences, and LinkedIn Learning.
• Well-being programs, EAP, local meetups, flexible time off.
• Salary range and equity; Employee Stock Purchase Program.
• DigitalOcean is an equal-opportunity employer.