Staff Applied AI Inference Engineer

Job overview

The Staff Applied AI Inference Engineer role is onsite in San Francisco, California. The posted compensation range is $215,000–$260,000 per year, plus bonus; restricted stock units are included in offers. Crusoe’s mission is to accelerate the abundance of energy and intelligence through AI infrastructure. The engineer optimizes large language model inference for speed, cost, and reliability in production. The role owns performance work across serving systems and customer deployments, translating workload requirements into tested optimizations that improve latency, throughput, and cost.

What you'll do

• Bring inference techniques into production
• design and optimize serving architectures
• profile frameworks and CUDA kernels
• adapt optimization methods across ML models
• tune deployments for latency, throughput, cost, and reliability
• partner with customer engineering teams to move workloads from proof of concept to monitored production
• build and support inference software
• run experiments and deliver tested results.

What we're looking for

Skills & competencies

staff engineer

applied ai

inference

large language models

llm serving

cuda

python

performance optimization

san francisco ca

crusoe

$215k–$260k

bonus

equity

customer deployments

Work arrangement

• Weekend coverage required

Benefits & perks

• Equity and restricted stock units, paid time off and holidays, health/dental/vision, HSA contributions, parental leave, life and disability insurance, professional development and tuition reimbursement, wellness support, commuter benefits, cell phone stipend, 401(k) match up to 4%, volunteer time off, travel insurance, and daily meal allowance.

Why this role

Hands-on systems and performance engineering role with customer-facing deployment work; Python is preferred, with experience in production code and LLM serving frameworks expected.

About the employer

Crusoe is hiring for this role. Industry: Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services. Sector: 51.