Senior ML Infrastructure Engineer

Kuzco is seeking a Senior ML Infrastructure Engineer to join their innovative team in San Francisco. The company is building a groundbreaking distributed LLM inference network that harnesses idle GPU capacity globally, managing over 5,000 GPUs and hundreds of terabytes of VRAM.

The role focuses on developing large-scale, fault-tolerant systems handling millions of LLM inference requests daily. You'll work at the intersection of distributed systems, machine learning, and resource optimization, designing and implementing core systems that power their globally distributed network.

The team consists of experienced staff-level engineers who have founded and run their own software companies. They value creativity, technical excellence, and humility, working in a high-agency, collaborative environment. The company offers competitive compensation ($180,000-$250,000), equity, and comprehensive benefits.

This position is perfect for someone with strong distributed systems experience, expertise in languages like TypeScript, Python, Go, or Rust, and a passion for ML infrastructure. You'll be working on cutting-edge technology that shapes the future of AI infrastructure, making this an exceptional opportunity for growth and impact in the AI industry.

The in-person work environment in downtown San Francisco provides direct collaboration with a dedicated team that's deeply passionate about their work. If you're excited about building next-generation ML systems at scale and want to be part of a well-funded, fast-growing startup, this role offers the perfect blend of challenge and opportunity.