Senior/Staff Software Engineer, Infrastructure

Ivo • San Francisco, CA

1d • $225,000 - $485,000 • Hybrid

About The Position

Infrastructure Engineers build the foundation for Ivo’s entire platform.

We’re looking for an Infrastructure Engineer to:
• Own and shape the future of our environment. We still have a relatively minimal footprint, giving you a lot of freedom to design the system.
• Manage dozens, hundreds, thousands (?) of customer deployments. Customers are cagey about their contracts, so each customer gets their own containers, database, VPC, etc. It’s a lot to orchestrate.
• Instrument our system so we understand performance bottlenecks, errors, etc.
• Aggregate metrics/logs/health checks into slick dashboards and pager alerts
• Be on call and lead infrastructure related incidents
• Get our CI/CD system running super quickly (it currently takes ~12 minutes, boo)

In addition to helping us run a solid, high-performance distributed system, we’d love someone who’s as excited about LLMs as we are. You’d be deeply embedded into the engineering team and encouraged to push the DevOps frontier by, for example:
• Developing on-the-fly LLM evals to monitor the real-time accuracy of our responses
• Building autonomous agents to detect and diagnose production issues before they become major fires
• Any other useful stuff you can think of

Mission
Every major business has an in-house legal team, and all of those lawyers are overworked. 80 hour weeks, tight deadlines and contract-reading death marches are the industry norm. Up until recently, there wasn’t anything technology could do to help this situation.

LLMs have given us the ability to give these lawyers their lives back, and at Ivo, that’s our mission.

We’re building an AI-native platform to automate legal drudgery. People love our software - despite high competition, we have the highest trial win rate on the market (85%). We’re genuinely improving people’s lives, and we’re only just getting started.

Ivo might be a good fit for you if you:
You love writing code, but you love having impact more: We’re a team of engineers at heart, but our #1 goal is building the best possible product. That means making pragmatic choices and looking for 80/20 solutions.
Would describe yourself as being relentlessly resourceful.
You have a strong internal sense of urgency. You have a bias towards doing things today, rather than tomorrow.
Experience working in a startup environment is preferred but not required.
Are excited about the adventure of building a company!

Nice To Haves

• Experience working in a startup environment is preferred but not required.

Responsibilities

• Own and shape the future of our environment.
• Manage dozens, hundreds, thousands (?) of customer deployments.
• Instrument our system so we understand performance bottlenecks, errors, etc.
• Aggregate metrics/logs/health checks into slick dashboards and pager alerts
• Be on call and lead infrastructure related incidents
• Get our CI/CD system running super quickly
• Developing on-the-fly LLM evals to monitor the real-time accuracy of our responses
• Building autonomous agents to detect and diagnose production issues before they become major fires

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed