Senior ML infrastructure engineer

ZipRecruiter; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Kuzco is seeking a Senior ML Infrastructure Engineer to develop large-scale, fault-tolerant systems for their distributed LLM inference network. Ideal candidates will have strong programming skills, a deep understanding of distributed systems, and a passion for building next-generation ML systems.

Benefits

Equity in a high-growth startup

Comprehensive benefits

Qualifications

• 5+ years of experience in building high-performance systems.
• Solid understanding of distributed systems concepts.
• Experience with LLM inference engines is a plus.

Responsibilities

• Design and implement scalable distributed systems for the inference network.
• Optimize network latency, throughput, and availability.
• Build robust logging and metrics systems to monitor network health.

Skills

Problem-solving

Distributed systems

Programming in Typescript

Programming in Python

Programming in Go

Programming in Rust

Programming in C++

AI tooling

GPU programming

Tools

Kubernetes

Nomad

vLLM

TensorRT-LLM

CUDA

Job description

Job Description

Kuzco is seeking a Senior ML Infrastructure Engineer to join our team. This role involves developing large-scale, fault-tolerant systems that handle millions of large model inference requests per day. If you are passionate about developing next-generation ML systems that operate at scale, we want to hear from you.

About Kuzco

We are building a distributed LLM inference network that combines idle GPU capacity from around the world into a single cohesive plane of compute that can be used for running large models like Llama and Mistral. At any given moment, we have over 5,000 GPUs and hundreds of terabytes of VRAM connected to the network. Learn more here.

We are a small, well-funded team of staff-level engineers who work in-person in downtown San Francisco on difficult, high-impact engineering problems. Everyone on the team has been writing code for over 10 years, and has founded and run their own software companies. We are high-agency, adaptable, and collaborative. We value creativity alongside technical prowess and humility. We work hard, and deeply enjoy the work that we do; we are almost always online at least six days per week.

About the Role

You will be responsible for designing and implementing the core systems that power our globally distributed LLM inference network. You'll work on problems at the intersection of distributed systems, machine learning, and resource optimization.

Key Responsibilities

1. Design and implement scalable distributed systems for our inference network
2. Develop models for efficient resource allocation across a network of heterogeneous hardware and quickly changing topology
3. Optimize network latency, throughput, and availability
4. Build robust logging and metrics systems to monitor network health and performance
5. Conduct reviews of architecture and system design to ensure use of best practices
6. Collaborate with founders, engineers, and other stakeholders to improve our infrastructure and product offerings

What We're Looking For

• Very strong problem-solving skills and ability to work in a startup environment
• 5+ years of experience in building high-performance systems
• Strong programming skills in Typescript, Python, and one of Go, Rust, or C++
• Solid understanding of distributed systems concepts
• Knowledge of orchestrators and schedulers like Kubernetes and Nomad
• Experience with AI tooling in development workflow (ChatGPT, Claude, Cursor, etc.)
• Experience with LLM inference engines like vLLM or TensorRT-LLM is a plus
• Experience with GPU programming and optimization (CUDA experience is a plus)

Compensation

We offer competitive compensation, equity in a high-growth startup, and comprehensive benefits. The base salary range for this role is $180,000 - $250,000, plus equity and benefits, depending on experience.

Equal Opportunity

Kuzco is an equal opportunity employer. We welcome applicants from all backgrounds and don't discriminate based on race, gender, age, disability, ethnicity, or veteran status.

If you're excited about building the future of developer-first AI infrastructure, we'd love to hear from you. Please send your resume, LinkedIn, and GitHub to [e-mail].