AI / LLM Engineer

Role overview

This position centers on designing and shipping LLM-powered features and agents that hold up beyond demos and prototypes. The work spans early experimentation through production deployment, with a strong emphasis on real-world reliability. It is a full-time, fully remote role open to candidates worldwide.

Responsibilities

- Build and iterate on LLM features and agent workflows intended for production use. - Evaluate model behavior under realistic conditions and harden systems against common failure modes. - Collaborate with engineering and product partners to take capabilities from idea to shipped. - Instrument, monitor, and refine deployed AI components based on observed performance.

Requirements

- Hands-on experience building applications on top of large language models. - Strong engineering fundamentals and the ability to take work end to end through production. - Familiarity with evaluation, prompt design, and common LLM orchestration patterns. - A pragmatic mindset for shipping AI systems that behave predictably under real-world constraints.

Benefits and work setup

- Full-time, fully remote position available to candidates globally.