Crusoe
Staff Applied AI Inference Engineer
$215K–$260K
San Francisco, CA - US · On-site · Staff · Full-time · Posted Sep 8, 2026
- Education
- Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
About the job
Optimizes and deploys production LLM inference systems, improving performance, reliability, and cost while working with customers to bring workloads from proof of concept to monitored production.
What you'll do
- Profile and optimize inference serving architectures, frameworks, and kernels for latency, throughput, and cost.
- Adapt inference optimizations to customer models and constraints, and deliver production services with monitoring.
- Build and support inference-stack software and product features; run experiments and own delivery through production.
What they ask for
- Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
- Production coding experience in one or more general-purpose languages, such as Python or C++.
- Familiarity with methods for optimizing LLM inference and modern serving frameworks such as vLLM or SGLang, including kernel-level performance analysis.
- Firm grasp of GPU architecture and behavior; hands-on experience and interest in large language models.
Nice to have
- Python is strongly preferred.
- Experience with CUDA or comparable technologies, Docker, Kubernetes, or customer-facing AI/ML projects.
Pay
up to $215,000 - $260,000 USD base salary + Bonus; Restricted Stock Units are included in all offers.
Tools
Python, C++, vLLM, SGLang, CUDA, Docker, Kubernetes
AI focus
Applied LLM inference engineering: optimize and deploy models for production performance, reliability, and cost.
Model-written summary · the original posting is authoritative