Staff+ Software Engineer, AI

📋 Description

• Own the shared AI foundation used by product teams, incl. model selection, routing, context mgmt
• Design architecture for consistent, reliable AI capabilities across product teams.
• Own AI evaluation infrastructure; define quality standards with customers and experts.
• Establish repeatable evaluation practices to measure model/agent performance.
• Build and ship agentic capabilities end to end from PoC to production.
• Apply prompt/context engineering, caching, parallel tool calls, subagent patterns to improve

🎯 Requirements

• Demonstrated experience building and shipping production LLM systems (eval infra, context mgmt
• Strong practical understanding of failures in production AI systems and improvements you
• Experience with LLM APIs and agent frameworks; track record of shipping user-facing AI products.
• Strong understanding of prompt engineering, context design, tool use, agent orchestration, caching
• Experience designing evaluation methodologies with measurable quality standards for LLM/agentic
• Strong architectural judgment; ability to create clear abstractions with simplicity and incremental

🎁 Benefits

• Fully remote work across the Americas.
• Location-based salary ranges and equity participation.
• Flexible hours for autonomy and remote collaboration.
• Unlimited paid time off.
• Regular in-person retreats and distributed team relationship building.
• Company-provided hardware.