Senior ML Ops Engineer

📋 Description

• Set up and maintain LLM observability tools
• Improve data annotation tooling
• Ensure stability of LLM calls (rate limits, throughput, backups)
• Support security reviews for AI vendors and providers
• LLM cost optimization: caching, batching, identify high-cost workflows
• Host finetuned/open-weight ML models

🎯 Requirements

• 5+ years building and operating software systems end-to-end
• Hands-on ML infra: model serving, training pipelines, or LLM integrations
• Strong understanding of cloud infrastructure and distributed systems (AWS)
• Familiarity with observability tooling and cost management for LLM workloads
• Experience with Python, Kubernetes, Terraform
• Thrives in a remote-first, async environment; high ownership, low ego