Sr. Lead AI Engineer - 11509

Mexico·Mexico CityRemoteMid-Senior Levelsenior

OtherLead Ai Engineer

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

Technical Tools

anthropicpythontypescript

Coupa makes margins multiply through its community-generated AI and industry-leading total spend management platform for businesses large and small. Coupa AI is informed by trillions of dollars of direct and indirect spend data across a global network of 10M+ buyers and suppliers. We empower you with the ability to predict, prescribe, and automate smarter, more profitable business decisions to improve operating margins.

Why join Coupa?

🔹 Pioneering Technology: At Coupa, we're at the forefront of innovation, leveraging the latest technology to empower our customers with greater efficiency and visibility in their spend.

🔹 Collaborative Culture: We value collaboration and teamwork, and our culture is driven by transparency, openness, and a shared commitment to excellence.

🔹 Global Impact: Join a company where your work has a global, measurable impact on our clients, the business, and each other.

Learn more on Life at Coupa blog and hear from our employees about their experiences working at Coupa.

We're looking for a senior Applied AI Engineer to help us build the harness that supplier agents run inside. You'll own platform-layer work: the skill framework, the tool layer that wraps Coupa APIs, the sandboxed execution environment, audit and replay logging, and the eval pipeline that tells us how it is all working. You'll also own the cloud infrastructure that runs it — how the platform is deployed, configured, and kept secure in production.

You'll start as a strong IC partnering with the team lead on architecture, and we expect you to ramp quickly into leading harness design yourself. This is a role for someone who wants ownership of a foundational system at the moment it's being built, not someone looking to maintain one that already exists.

Design and build the agent harness — skill loading, tool invocation, context management, the execution sandbox, compaction patterns and sub-agents.

Stand up the evaluation pipeline: how we measure skill effectiveness, catch regressions, and turn production failures into fixed behaviors.

Partner with product and engineering to ship the first 3–5 supplier-facing use cases (invoicing, catalog, strategic views) on top of the platform you build.

Define and maintain the cloud deployment and configuration for the platform. How it gets to production, how it scales, and how it stays secure.

Make architectural calls on runtime isolation, credential handling, audit logging, and tenant separation, in collaboration with DevOps specialists.

Raise the bar for the rest of the team on how to build with agentic tooling, what to automate, what to verify, and what to leave to humans.

Have 6+ years shipping production software and are strong in Python and/or TypeScript.

Have built platform or infrastructure systems that other engineers depend on — CLIs, runtimes, internal platforms.

Have shipped at least one LLM-powered product to real users and have opinions about why most of them don't work.

Are a daily, heavy user of agentic coding tools — Claude Code, Cursor, Codex, or equivalents — and have a point of view on how to get the most out of them.

Have side projects. Real ones. Things you've built because you couldn't stop thinking about them. Ideally things the new generation of AI tools made possible for you to finish.

Write and speak English fluently — skill authoring is prose-heavy and the team operates in English.

Have deployed and operated containerized services in production. You understand network isolation, infrastructure-as-code, secrets management, and least-privilege IAM, not just the application layer.

Think in systems: you reason about tokens, latency, failure modes, and user outcomes together, not as separate concerns.