Staff AI Systems Engineer

📋 Description

• Deploy, scale, and manage AI infra for training and low-latency inference.
• Use MLflow for experiments and model registry to streamline AI lifecycle.
• Optimize compute and inference; multi-cloud scheduling and LLM serving.
• Collaborate with researchers and engineers to productionize models and monitor performance.

🎯 Requirements

• Education: BS/MS/PhD in Computer Science, Software Engineering, or related field.
• Experience: 5+ years in software engineering focused on AI/ML systems, HPC, or ML infra.
• Multi-Cloud & Compute: AWS plus AI-centric bare-metal and GPU clouds (Nebius AI Cloud).
• Cloud-Native Orchestration: Docker and Kubernetes; SkyPilot for multi-region GPU availability.
• LLM Serving: Deep understanding of LLMs and infra; frameworks like vLLM and SGLang.
• Data Engineering for AI: High-throughput data pipelines; SQL, NoSQL, Parquet.

🎁 Benefits

• Equal opportunity employer committed to diversity.
• Reasonable accommodations available for applicants.
• Merit-based, performance-driven culture.