Senior Director, Inference Products and Optimizations

📋 Description

• Lead and develop engineers; foster ownership and excellence.
• Define and drive roadmap for Inference products: Serverless, Dedicated, Router, Batch.
• Architect inference serving; optimize throughput, latency, GPU utilization.
• Partner with PMs and teams; align priorities and dependencies.
• Ensure production health, stability, and on-call rotation.
• Institutionalize benchmarking, observability, and auto-tuning; OSS.

🎯 Requirements

• 10+ years software engineering; 6+ years in leadership.
• Distributed systems, Kubernetes at scale, LLM inference.
• GPU architectures (NVIDIA/AMD), NVLink, hardware topology.
• Container runtimes, system isolation, security contexts.
• Observability and SLOs; metrics-driven performance.
• Product mindset, communication, ownership.

🎁 Benefits

• This is a remote role.
• Reimburse conferences, training, and LinkedIn Learning.
• Well-being benefits, Local Meetups, flexible time off.
• Equity grants and Employee Stock Purchase Program.
• DigitalOcean is an equal-opportunity employer.
• Global benefits with local variations.