Infrastructure Engineer

San Francisco, CA · On-site · Full-timeCompensation: $150,000–$250,000 + 0%–1% equity

About the Company

Our client does LLM interpretability and context-optimization research, building custom machine-learning models that analyze and compress token contexts before they reach the underlying model. The result is roughly a 50% inference-cost reduction, lower latency, and measurably higher accuracy for the enterprises and scale-ups integrating LLMs into their products. About seven months old, it already serves roughly 1,000 customers and is well-backed by top-tier investors and notable operators.

Founded 2025 · 1–10 people (Seed) · Industry: AI Tools

The Role

Own the full multi-region GPU infrastructure stack end to end as the sole infra hire — global low-latency serving, multi-cloud and on-prem deployments, reliability, and cost efficiency — for a seed-stage LLM context-compression company. In-person in SF at a high-intensity pace.

Tech stack: AWS, GCP, Base10, Terraform, Docker, CI/CD, GPU/ML inference infrastructure, AWS Marketplace.

What you'll be doing

• Own the cloud systems serving the compression API end to end
• Build and operate global, low-latency, high-throughput GPU ML inference infrastructure
• Work across AWS, Terraform, Docker, and CI/CD
• Continuously improve and research infrastructure solutions

Requirements

• Has built and operated production infrastructure at a startup or larger company
• Learns new solutions and technologies quickly
• Based in or willing to relocate to San Francisco to work in person at the hacker house
• Willing to work startup hours in a high-intensity (9am–9pm, six-day) environment

Nice to Haves

• A quick learner who grasps products and systems fast
• Experience building for performance and reliability at scale
• A research-and-product-focused mindset
• A high-ownership mentality
• A startup-minded operator who prioritizes learning and growth over work-life balance
• GPU-infrastructure experience in production, or a background at an infrastructure company
• First infra-hire experience at a startup

Why Join

• Sole infra owner, full stack, day one: own every layer of a multi-region GPU stack (AWS, GCP, Base10, on-prem), sitting directly in the critical path of ~1,000 customers
• Strong backing and early traction: ~1,000 customers within seven months, well-funded by top-tier investors
• Comp and lifestyle support for high output: $150K–$250K + up to 1% equity, with housing and food provided at the SF hacker house, visa sponsorship, laundry/cleaning, meal delivery, and health/dental

Details

• Location — San Francisco, CA
• Work policy — On-site, high intensity (six days/week)
• Compensation — $150,000–$250,000 + 0%–1% equity
• Visa sponsorship — Available (H-1B, O-1, OPT)
• Employment type — Full-time