At Guided, we build real-time agents that keep the wheels of the transportation industry spinning. Our AI works across voice, text and legacy systems to handle all the messy manual touch points needed to move anything from anywhere to anywhere.

We’re backed by Sequoia, growing fast and working with leading transport companies. To keep pace with customer demand, we’re hiring an AI Engineer to own the full lifecycle of our agent workflows — from prototype to production, evals to reliability at scale.

This isn’t research. It’s applied AI with feedback loops measured in minutes, not weeks.

The role

• Your mission is to bridge user needs with the latest AI advancements, building production-grade agents that enhance operational workflows in logistics
• Own and evolve our LLM pipeline: from prompt design, grounding, evals, and testing to live performance in production.
• Build tools to scale agent behaviour across our customer use cases, enabling us to fine tune LLMs at scale
• Improve agent reliability through better fallback design, error handling, and feedback loops
• Architect the product from user experience to technical architecture
• Ensure agents behave consistently across user segments, languages and customer-specific workflows

You will be a good fit if you …

• Have a passion for the latest in AI: building and deploying LLM-based systems at work or in your free time
• Have familiarity with our tech stack: Node JS, Typescript, Python
• Are obsessive about product, often working nights and weekends in the pursuit of building something great
• Enjoy being a generalist, willing to work on everything from testing models to managing our cloud infrastructure to writing user guides to ...
• Biased to action and understand that we need to move fast, experiment and iterate as we go

You will not be a good fit if you …

• Need highly scoped tickets to get started
• Optimise for technical purity over real-world outcomes
• Dislike user discovery, being onsite and learning from customers