Rust Engineer

LiteLLM•San Francisco, CA

10d

About The Position

LiteLLM is the world's most popular AI Gateway, trusted by top companies like Adobe, Netflix, and NASA. Our platform empowers developers by providing secure, reliable access to LLMs and adjacent services. We're looking for a Rust Engineer to own the migration of LiteLLM from Python to Rust and make us the fastest AI gateway ever built. About The Role You'll own LiteLLM's migration to Rust end to end. This is a high-stakes, high-visibility role: you'll plan the migration directly with the CTO, structure the codebase so it's ready for Rust, and lead a gradual, stability-first rollout. The work is fundamentally about performance. Every decision you make will move us toward being the lowest-latency, highest-throughput gateway in the category, without ever compromising the reliability our enterprise customers depend on. This is a single-owner mandate. You will be the person leading the entire Python-to-Rust migration.

Requirements

Deep, long-standing expertise in Rust. You've been writing production Rust for years and know it cold.
Obsessive about performance. You care about latency and throughput at a level most engineers don't.
Strong instinct for stability, with a track record of balancing ambitious change against reliability.
Familiarity with backend infrastructure, databases (PostgreSQL, Redis), and high-volume production systems.

Nice To Haves

Prior experience leading codebase migrations from another language to Rust.
A demonstrated history of shipping performance-critical systems.

Responsibilities

Own the end-to-end migration of LiteLLM from Python to Rust, from architecture through rollout.
Plan the migration alongside the CTO, sequencing work to minimize risk to live, high-volume traffic.
Design and execute a gradual rollout that holds stability as the top constraint while the migration progresses.
Restructure the existing codebase so it's positioned for a clean, incremental move to Rust.
Drive performance gains across latency, throughput, and resource efficiency at 1B+ requests/mo.
Collaborate cross-functionally to ensure the migration aligns with backend priorities across performance, reliability, and security.