Build at the frontier of AI infrastructure

🧠

Hard Problems

Work on some of the most challenging systems problems in AI: serving trillion-parameter models at millisecond latencies across a global network.

📈

Massive Scale

Our platform processes 2.4M requests per second. Every optimization you ship impacts millions of developers and billions of API calls.

🏆

World-Class Team

Work alongside engineers from Google, Meta, NVIDIA, and top research labs. Our team has published 100+ papers at top venues.

💰

Competitive Comp

Top-of-market salary, meaningful equity, and comprehensive benefits. We believe in paying fairly for exceptional talent.

🌎

Remote-First

Work from anywhere. We have team members across 12 countries with offices in SF, NYC, and London for those who prefer in-person.

📚

Learning Budget

$5,000 annual learning budget for conferences, courses, and books. Plus dedicated time for research and open-source contributions.

Perks & benefits

We take care of our team so they can do their best work.

💰

Top Compensation

Top-of-market salary + meaningful equity. Annual refreshers based on performance.

🏥

Health & Wellness

Premium medical, dental, vision. Mental health support. $1,200/yr wellness stipend.

🌴

Flexible PTO

Unlimited PTO with 4-week minimum. Company shutdowns in summer and winter.

🏠

Remote-First

Work from anywhere. $3,000 home office setup. Co-working space stipend available.

📚

Learning Budget

$5,000/year for conferences, courses, books. Dedicated research time.

👶

Parental Leave

16 weeks paid parental leave for all parents. Flexible return-to-work options.

💻

Equipment

Latest MacBook Pro or Linux workstation. Additional monitors and peripherals provided.

✈️

Team Offsites

Quarterly team offsites in exciting locations. Annual company-wide gathering.

Current openings

We're growing fast. Find your next role below.

Engineering

Senior CUDA Engineer

San Francisco / RemoteFull-time$250K–$350K
Apply →

Staff Systems Engineer — Inference Serving

San Francisco / RemoteFull-time$280K–$380K
Apply →

Senior Backend Engineer — API Platform

RemoteFull-time$200K–$280K
Apply →

Infrastructure Engineer — Kubernetes & GPU Orchestration

RemoteFull-time$200K–$270K
Apply →

Senior Frontend Engineer — Developer Console

RemoteFull-time$180K–$250K
Apply →

Research

Research Scientist — Model Optimization

San Francisco / RemoteFull-time$250K–$350K
Apply →

Research Engineer — Quantization & Compression

RemoteFull-time$220K–$300K
Apply →

Product & Design

Senior Product Manager — Developer Platform

San FranciscoFull-time$200K–$280K
Apply →

Senior Product Designer

RemoteFull-time$180K–$240K
Apply →

Go-to-Market

Enterprise Account Executive

San Francisco / NYCFull-time$150K–$200K + commission
Apply →

Developer Advocate

RemoteFull-time$160K–$220K
Apply →

Our interview process

We respect your time. Our process is designed to be efficient, transparent, and fair.

1

Application Review

We review every application within 5 business days. No AI screening — real engineers read your resume.

2

Technical Screen

45-minute video call with an engineer. Discussion of your experience and a focused technical problem.

3

Deep Dive

Take-home project or pair programming session (your choice). Designed to take 2-3 hours max.

4

Team Interviews

Meet the team in 3-4 focused sessions. System design, collaboration, and values alignment.

Average time from application to offer: 2 weeks. We provide feedback at every stage.

Don't see your role?

We're always looking for exceptional people. Send us your resume and tell us what you'd like to work on.