Zep AI

The unified context layer for enterprise data

Zep manages, governs, and serves agent memory at enterprise scale. Enterprises build on Zep to run reliable, personalized agents across the business: millions of Context Graphs, served in under 200ms, inside their own VPCs and cloud deployments. Customers include Zscaler, Samsung, Twin Health, HoneyBook, and NASDAQ 100 and Fortune 500 technology companies. We also build Graphiti, our open-source context graph framework (30K+ GitHub stars). Getting Zep into production in customer environments is its own engineering problem, and you own it.

You will lead our deployments and build the team that runs them. The first year is hands-on. You will be in architecture reviews and in our codebase, and on site when a deployment needs you. Our engineers work deployments alongside you, so you are never the only technical person on the call.

We're hiring an engineer and leader who has done this work and can now set the standard for how we do it.

This is note a core product engineering role. You should have significant customer-facing experience in an FDE, sales engineering, or field engineering role.

We will measure you on time from signature to production, and on custom engineering per deployment.

You’ll report to our founder, Daniel (2x founder, engineer, former head of ML at SparkPost), and join a team with pedigree at Scale AI, Dropbox, ActiveCampaign, DroneDeploy, and McKinsey.

How we work

We're a small, distributed team that works closely together. We pair on hard problems, review each other's designs, and treat learning as part of the job rather than something that happens after hours. We ask a lot of questions: of customers, of teammates, of our own assumptions. When we find pain, we go fix it.

We expect the same back: ask questions early, push back when you disagree, and care about the people on the other end of the API.

What you'll do

• Own the technical outcome for our largest accounts, from the first architecture conversation through 90 days in production.
• Write code. Integration work, reference architectures, deployment tooling, and fixes in the product itself.
• Deploy Zep inside customer infrastructure across Managed, BYOK, and BYOC, and work directly with the platform and security teams who have to approve it.
• Define the engagement model. Decide which accounts get embedded support, and set how that work is scoped and priced.
• Hire the team. You define the bar and lead the engineers you bring in.
• Reduce the custom work each deployment takes. What you build twice becomes a reference architecture or a product requirement.
• Take what you learn in production back into the roadmap. You will be in planning with the engineers who can act on what you bring.

Your first 90 days

You start inside a live deployment: shipping code, meeting the customers we already serve, and learning how Zep runs in their environments. By day 60 you own every active deployment. By day 90 you have written the first version of the engagement model.

\What we're looking for

• 10+ years across software engineering, forward deployed engineering, solutions architecture, or sales engineering, with several of those years as a hands-on engineer.
• You have taken enterprise deployments from first call to production under a security review and a fixed deadline.
• 3+ years leading customer-facing technical people, or a clear case for why you are ready to.
• Strong Python, plus Go or TypeScript. You will read our codebase and send patches.
• You have shipped a non-trivial agentic system to production. Not a prototype, not a thin wrapper over a chat-completion API.
• Comfortable in customer infrastructure: AWS, Kubernetes, Terraform, and the identity and encryption work a BYOC install requires.
• You raise risks early, including when it is inconvenient for the person you are talking to.

This role is probably NOT a fit if:

• You have run a professional services P&L and think of this as a delivery org.
• Your customer-facing work ends with the technical win and a handoff at signature.
• You haven't written production code in several years and don't intend to start again.
• You need an established playbook or sign-off before you move.

We respect your time and keep our interview process tight and focussed.

• Screening Call (w/ Daniel, our Founder)
• → Team Calls (2-3 hours back-to-back, including a deployment scenario walkthrough)
• → Decision Call (Daniel, again)