Lead AI Engineer
Job Description
About The Team And What We'll Build Together
Kobie runs some of the largest loyalty programs in the world. We're building an internal agent platform on Amazon AgentCore that automates analyst workflows, surfaces insights from program data in Snowflake, and gives our teams an LLM-native way to work with complex loyalty logic.
We're looking for a hands-on Lead AI Engineer to ship the hardest implementation work on that platform. You'll author the per-feature implementation specs that turn architectural decisions into work the team and our code agents can build against. You'll also build the load-bearing pieces yourself — the human-in-the-loop routing primitive, the reversibility-tier execution wrapper, the guardrails that make agent actions safe to deploy — and review PRs at a depth that lifts the standard for what we ship.
Our team tends to be people who reason carefully, ship working code, and pick up new tools without a lot of hand-holding. We care less about the shape of your career than whether you've built things that held up.
How We Think About AI
We're building agents for an industry — loyalty marketing — that runs on judgment. The analysts and strategists we serve know things that don't live in any database: which clients can hear which feedback, when a campaign is technically sound but commercially wrong, what a number means versus what it shows. Our agents make their judgment go further; they don't replace it.
That means we have strong views on where agents should and shouldn't act. As Lead, you turn those views into running code: which tools route to a human for approval, which run autonomously, what the refusal policies actually refuse. We're looking for someone with a considered view on cognitive offloading, the long-term effects of agent-mediated work on organizational capacity, and the discipline to build implementation safeguards that augment human judgment rather than supplant it.
About The Team And What We'll Build Together
Kobie runs some of the largest loyalty programs in the world. We're building an internal agent platform on Amazon AgentCore that automates analyst workflows, surfaces insights from program data in Snowflake, and gives our teams an LLM-native way to work with complex loyalty logic.
We're looking for a hands-on Lead AI Engineer to ship the hardest implementation work on that platform. You'll author the per-feature implementation specs that turn architectural decisions into work the team and our code agents can build against. You'll also build the load-bearing pieces yourself — the human-in-the-loop routing primitive, the reversibility-tier execution wrapper, the guardrails that make agent actions safe to deploy — and review PRs at a depth that lifts the standard for what we ship.
Our team tends to be people who reason carefully, ship working code, and pick up new tools without a lot of hand-holding. We care less about the shape of your career than whether you've built things that held up.
How We Think About AI
We're building agents for an industry — loyalty marketing — that runs on judgment. The analysts and strategists we serve know things that don't live in any database: which clients can hear which feedback, when a campaign is technically sound but commercially wrong, what a number means versus what it shows. Our agents make their judgment go further; they don't replace it.
That means we have strong views on where agents should and shouldn't act. As Lead, you turn those views into running code: which tools route to a human for approval, which run autonomously, what the refusal policies actually refuse. We're looking for someone with a considered view on cognitive offloading, the long-term effects of agent-mediated work on organizational capacity, and the discipline to build implementation safeguards that augment human judgment rather than supplant it.