AI Systems Engineer

📋 Description

• Build production AI inference systems for in-house models.
• Focus on model serving, runtime optimization, and deployment safety.
• Run low-latency services on NVIDIA GPUs in GCP.
• Define packaging, benchmarking, monitoring, and rollout processes.
• Create scalable, observable inference platforms across environments.
• Collaborate with model developers and infrastructure teams.

🎯 Requirements

• 6+ years in production software or infra.
• Python or Go backend development.
• Experience with high-throughput services or ML infra.
• Kubernetes, Linux, CI/CD, deployment automation.
• Strong debugging and systems thinking.
• Model-serving frameworks like vLLM, Triton.
• Collaborates with model developers and infra teams.

🎁 Benefits

• Work at the center of AI transformation.
• Build agentic AI products redefining operations.
• AI amplifies every employee’s impact.
• Competitive salary and comprehensive benefits.
• Great Place to Work culture.