Infrastructure Engineer

About the role

WHY JOIN IVO?

Contracts are the oldest business technology in human history. They allow us to collaborate: they define what we promise each other, how we work together, and what happens when things go wrong.

Ivo builds AI products that helps companies like Meta, Uber, IBM, Intel, DoorDash, Mitsubishi Electric, and Coinbase solve their most difficult contracting problems. We think that large language models have created an opportunity to fundamentally change how businesses collaborate with each other.

At Ivo you will work on challenging problems with colleagues who have high standards for each other, move fast, and care deeply about their craft.

ENGINEERING AT IVO

Engineers at Ivo are inventors. Ivo was first-to-market with:

- An AI agent that lives in MS word and edits the document for you [2023]

- Ditching imprecise embeddings models in favor of agentic RAG [2023]

- Large-scale LLM-based legal fact extraction [2024]

- A legal assistant that can search large contract databases, without sacrificing accuracy [2024]

- Clustering legal documents descended from the same family [2025]

- Automatic deviation analysis to locate buried risk in huge contract databases [2025]

- Merging contracts with their amendments to make a time series of “composite” contracts (a customer actually cried when we showed her this) [2025]

THE ROLE: WHY, WHAT AND THE WHO

Why? Infrastructure Engineers build the foundation that our products need to perform efficiently and effectively. Customers are cagey about their contracts, so each customer gets their isolated environment with containers, database, namespace, etc. When things break or go down, Cloud and LLM providers have “incidents.” And of course, our customers still expect us to hit our SLAs.

What? You do not need to have experience with all of these things, but they should excite you.

- Run Kubernetes like it's your own startup within the startup. Own multi-cluster, multi-region deployments across AWS/GCP/Azure, with failover and disaster recovery that actually works when it matters (not just on paper)

- Tools for infra. Build internal tools for creating and managing clusters so dev to production is consistent.

- Isolated workloads. ML vs. API traffic has very different needs. Design the strategy that balances cost, performance, and reliability without over-engineering it

- Security. Customers need to trust us; product velocity should not suffer for security reasons. Things like RBAC, workload identity, secrets management, data residency, and audit trails need to be invisible though critical.

- Honest SLO/SLIs. Create targets that are enforceable and won't trigger alerts at 3am for nothing.

- Own pipelines. GitHub Actions for CI/CD and Pulumi for IaC.

- Docker environments. Across dev, staging, and prod

- Bugs. Infra should be detective level good at finding bugs within the entirety of the the engineering environment. Frontend, backend, etc.