We’re building an open-source platform to create a feedback loop for optimizing LLM applications—turning production data into smarter, faster, and cheaper models. Our goal is to unify inference, observability, optimization, and experimentation into a seamless learning flywheel for LLMs.

The Role
We’re looking for a Founding Member of Technical Staff with expertise in back-end and systems engineering, particularly Rust. Our model gateway, written in Rust, powers everything we do. If you join today, you’ll work on features like inference-time optimizations and advanced experimentation tooling, while shaping the platform’s technical backbone.

Who You Are

Systems Expert: You bring strong technical leadership and have experience tackling complex back-end challenges. Rust Proficiency: Comfortable working with and building robust, efficient infrastructure in Rust. Growth-Oriented: Excited to expand your skills beyond systems engineering, diving into areas like ML or distributed systems. Collaborative: Energized by working in-person with a small, focused team in NYC.

What We Offer

Competitive compensation, including salary, equity, and benefits. Open-source focus: most of your work will be public. A small, technical, in-person team where you’ll have a direct impact on the vision and engineering culture. Best-in-class investors and a long-term mindset to focus on innovation.

Join us in building the future of LLM optimization from the ground up.