Senior AI Inference Engineer: Production LLM Performance

Crusoe Energy Systems; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Health benefits

Paid time off

401(k) match

Mental wellness

Job summary

Crusoe Energy Systems is seeking a hands-on engineer to accelerate large language model inference in production. You will own the inference stack end to end, profiling time and cost, and bring optimization techniques into real deployments.

You will work directly with customer teams to tailor deployments, move workloads from proof-of-concept to live production services, and ensure improvements are measurable and reliable in high-traffic scenarios.

Qualifications

• Hands-on production experience shipping code in Python or C++.
• Strong background in performance optimization for ML workloads.
• Experience with Docker and Kubernetes in production environments.

Responsibilities

• Own the inference stack end to end, profiling time and cost in production.
• Collaborate with customer teams to tailor deployments to needs and latency targets.
• Design and optimize serving architectures including prefill and decode strategies.
• Analyze performance down to kernel level and ship well-tested results.

Skills

Python

C++

Docker

Kubernetes

CUDA

LLM serving

Profiling & optimization

Software performance

Education

Bachelor’s/Master’s/Ph.D. in CS/Engineering/Math

Tools

vLLM

SGLang

GPU architectures

Job description

Crusoe Energy Systems is seeking a hands-on engineer to accelerate large language model inference in production. You will own the inference stack end to end, profiling time and cost, and bring optimization techniques into real deployments.

You will work directly with customer teams to tailor deployments, move workloads from proof-of-concept to live production services, and ensure improvements are measurable and reliable in high-traffic scenarios.