Head of LLM Inference Platform & Architecture

United States Digital Space LLC; San Francisco (CA); On-site; USD 240,000 - 360,000; Full time

Job summary

United States Digital Space LLC is building an infrastructure layer for AI workloads, delivering frontier performance with a multi-cloud substrate and low-latency inference for customers. We are seeking a hands-on engineering leader to own the direction of the LLM inference platform, drive architecture, and grow a high-performing team while partnering with customers and cross-functional teams.

You will balance technical contribution with product shaping and people management, setting standards

Qualifications

• 10+ years of industry experience, including 3+ years in a leadership role.
• Track record building high-performance systems at scale.
• Strong background in cloud infrastructure.
• Deep knowledge of low-level OS foundations (Linux kernel, filesystems, containers).
• Nice to have: production experience with LLM inference; engines, kernels, routing, KV cache management, speculative decoding.

Responsibilities

• Recruit, hire, and grow a high-performing team of engineers; conduct regular 1:1s focused on coaching, feedback, and career growth.
• Set clear performance expectations, hold a high bar, and build an environment where engineers do their best work.
• Foster a culture of ownership, accountability, customer obsession, and continuous improvement.
• Drive technical and product decisions through design reviews, code reviews, and architectural discussions.
• Lead our efforts working with customers with frontier workloads so they can be successful running on the company.
• Translate learnings from frontier customers into a roadmap for our internal optimization platform and user-facing product, so that gains from optimization and research efforts are accessible to all of our users.
• Establish standards for reliability and product excellence; ensure the team owns projects end-to-end, from spec through production.
• Partner with business operations and compute strategy on continuing to develop our strategy for compute purchases across a variety of accelerators.
• Collaborate with GTM on product launches, positioning, and improving win rates for inference opportunities.
• Help guide the roadmap for teams building the infrastructure platform underlying inference, as well as adjacent product teams.

Skills

Leadership experience

Distributed systems

Cloud infrastructure

Team building

Performance optimization

Tools

Linux kernel

Containers

Job description

United States Digital Space LLC is building an infrastructure layer for AI workloads, delivering frontier performance with a multi-cloud substrate and low-latency inference for customers. We are seeking a hands-on engineering leader to own the direction of the LLM inference platform, drive architecture, and grow a high-performing team while partnering with customers and cross-functional teams.

You will balance technical contribution with product shaping and people management, setting standards