Staff Applied Ai Inference Engineer

Staff Applied AI Inference Engineer at Crusoe focused on optimizing large language models for production. This role involves end-to-end ownership of the inference stack, profiling performance and cost, applying optimization techniques, and deep dives into serving code. The work is applied, directly impacting customer deployments with varying models, traffic, and constraints.

Skills and focus areas

• applied ai
• inference optimization
• large language models
• production deployment
• performance profiling
• cost optimization
• serving code
• customer engineering
• problem-solving
• systems engineering