Senior AI Inference Engineer — Production LLM Optimizer

Crusoe Energy Systems LLC; San Francisco, Northern (CA, KY); Hybrid; USD 250,000 - 300,000; Full time

Benefits offered by this job

Competitive compensation

Equity packages

Health/dental/vision insurance

Paid time off

Job summary

Crusoe Energy Systems LLC seeks a hands-on systems engineer to optimize large language model inference in production. You will own the inference stack end to end—from profiling costs to deploying optimizations on real workloads, working with customer teams to tailor deployments.

The role emphasizes coding, profiling, and low-level optimization, with a customer-facing element and contributions to product requirements.

Qualifications

• Hands-on experience shipping production code in Python or C++.
• Experience optimizing LLMs for high throughput and low latency.
• Familiarity with LLM serving frameworks (vLLM, SGLang).
• Understanding GPUs and CUDA basics for performance tuning.

Responsibilities

• Own the inference stack end to end in production, profiling cost and latency.
• Collaborate with customer engineering teams to tailor deployments.
• Implement and ship optimization techniques for diverse models and workloads.
• Work with frameworks like vLLM/SGLang, profiling down to kernels.
• Translate goals into concrete specs and proofs of concept.

Skills

Python

C++

GPU architectures

Python optimization

LLM inference

vLLM

SGLang

Profiling

Communication

Education

Bachelor's degree in CS/Engineering/Math

Master's or PhD (preferred)

Tools

Docker

Kubernetes

CUDA

Job description

Crusoe Energy Systems LLC seeks a hands-on systems engineer to optimize large language model inference in production. You will own the inference stack end to end—from profiling costs to deploying optimizations on real workloads, working with customer teams to tailor deployments.

The role emphasizes coding, profiling, and low-level optimization, with a customer-facing element and contributions to product requirements.