AI Engineer

Job Summary

To build and harden the platform for LLM-based products, the full-time remote AI Engineer will develop reusable capabilities, ensure safe execution of long-running agents, and optimize cost per task while collaborating with product engineers to enhance AI features.

Key responsibilities

• Harden the platform for reuse by making first-version capabilities reusable across multiple use cases
• Design state management and deployment patterns for safe execution of long-running agent tasks
• Optimize model routing and token usage to reduce costs as the platform scales

Required qualifications

• Experience with infrastructure for LLM-based products, including agent runtime and context management
• Proven track record of shipping LLM features to production and managing trade-offs in model behavior
• Proficiency in modern full-stack development using TypeScript and/or Python
• Practical habits in evaluation and tracing of model outputs
• Ability to communicate technical decisions to product and design teams effectively