Senior AI Inference Engineer — Production-Scale LLM Optimization

Fdetimes; San Francisco (CA); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Competitive compensation

Equity

Health, dental, vision insurance

Job summary

Crusoe is seeking an engineer to make large language models run faster, cheaper, and more reliably in production. You will own the inference stack end to end, from profiling time and cost to deploying optimized CUDA kernels and serving code for real customer workloads.

The role combines core systems work with customer-facing responsibilities, product insights, and hands-on coding in Python (preferred) with collaboration across engineering and product teams.

Qualifications

• Bachelor's degree in CS or related field.
• Experience shipping production code in Python or C++.
• Familiarity with optimizing LLMs for throughput/latency.
• Understanding GPUs and kernel-level profiling.
• Good communication with customers and teammates.

Responsibilities

• Design and optimize inference serving architectures for LLMs.
• Profile and tune deployments to meet latency, throughput, and cost targets.
• Work with customer teams to tailor deployments to their needs.
• Ship production-ready optimizations and document requirements.

Skills

Python

C++

LLM optimization

Profiling

GPU architectures

Communication

Education

Bachelor's degree in CS or related field

Tools

vLLM

SGLang

CUDA

Docker

Kubernetes

Job description

Crusoe is seeking an engineer to make large language models run faster, cheaper, and more reliably in production. You will own the inference stack end to end, from profiling time and cost to deploying optimized CUDA kernels and serving code for real customer workloads.

The role combines core systems work with customer-facing responsibilities, product insights, and hands-on coding in Python (preferred) with collaboration across engineering and product teams.