Staff Engineer, Systems and Reliability

LiteLLM; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Relocation assistance

Competitive compensation

Health, dental, and vision benefits

Direct collaboration with founders

Job summary

LiteLLM is seeking a Staff Engineer to own the stability and reliability of the AI gateway used by thousands of companies. This hands-on role focuses on root-cause analysis, refactors, and bold rewrites to prevent regressions and security issues, with immediate production impact.

You will work closely with security and infrastructure teams, report to the CEO (then Head of Engineering), and contribute to a fast-moving, in-person SF environment. relocation support available.

Qualifications

• 3+ years of experience and growing scope at a strong engineering company.
• Owned stability or reliability in production environments.
• Led rewrites or migrations to improve code quality.
• Walk into unfamiliar codebases and find root causes.

Responsibilities

• Find root causes of regressions and security issues and fix patterns.
• Lead refactors, rewrites, and migrations of core product code.
• Decide what makes our test suite trustworthy and build it.
• Keep CI and releases fast and trustworthy with a large open source contributor base.
• Review critical code paths and raise quality through code and reviews.
• Raise quality across the team without becoming the bottleneck.

Skills

Experience 3+ years

Stability & reliability

Root cause analysis

First principles thinking

Customer empathy

Python engineering

Open source/CI experience

Tools

CI/CD pipelines

Open source contributions

Job description

LiteLLM is the world’s most popular AI Gateway, trusted by companies like Adobe, Netflix, and NASA. We’ve grown ARR 6x in the last year to nearly $30M with a team of 20, and thousands of companies run production AI through LiteLLM across 100+ provider integrations.

We're looking for a Staff Engineer to own the stability and reliability of the gateway.

About the role

This is a hands-on staff role. You'll find the components behind our regressions and security issues, and refactor or rewrite them so the same problem doesn't come back in 20 places. You'll raise the quality of the codebase through your own code and review, not process documents.

LiteLLM is mission-critical infrastructure for our customers. When it breaks, their AI products break. You'll make sure that happens less, and that we know before they do.

You’ll work with our security and infrastructure team and report to the CEO, and later to our Head of Engineering. This role is in person in San Francisco. We help with relocation and support H-1B transfers.

Responsibilities

• Find the root causes of regressions and security issues and fix the patterns that create them.

• Lead refactors, rewrites, and migrations of core product code on a system our customers can't afford to have go down.

• Decide what makes our test suite worth trusting, and build it.

• Keep CI and releases fast and trustworthy with a large open source contributor base.

• Review the code paths that matter most and raise the bar through your own code and review.

• Raise quality across the team without becoming the bottleneck.

What is our tech stack

The tech stack includes Python, FastAPI, Redis, Postgres. We're moving the gateway to Rust.

What we're looking for

• 3+ years of experience, with a fast rise in scope at a strong engineering company. The scope you've owned matters more than a Staff title.

• You've owned stability or reliability at your current company.

• You've owned mission-critical systems in production and led rewrites or code migrations.

• Able to walk into an unfamiliar codebase and find the real root cause.

• A first principles thinker. You reason through a hard bug or a large refactor yourself, and you review AI-written code as carefully as any other.

• Customer empathy. You think about what a change does to users before you ship it.

• Strong software engineering fundamentals, preferably in Python.

• You don't need a security background: our security team finds the issues, and you fix the patterns behind them.

Bonus points

• Rust experience.

• You've kept CI healthy on an open source project with heavy outside contribution.

• Experience at an early-stage startup.

Why join LiteLLM?

• Work directly with the founders every day.

• Own the reliability of infrastructure that thousands of companies run in production.

• Own a whole area of the codebase. We don't have PMs: engineers talk to customers and decide what to build.

• Your work ships in open source, used by engineering teams around the world.

• Move incredibly fast and see your work in production immediately.

• Competitive salary, equity, health, dental, and vision benefits.

About LiteLLM

LiteLLM is the world's most widely adopted AI Gateway. We provide a unified API for 100+ LLM providers along with routing, authentication, budgets, observability, and governance for production AI systems. Thousands of companies rely on LiteLLM to power AI in production.

If you want to own the reliability of the gateway thousands of companies depend on, we'd love to meet you.