Crusoe designs, builds, and operates energy-first AI infrastructure. Its offerings include Crusoe Cloud for GPU-based training, fine-tuning, inference, and managed services, alongside AI-optimized data centers and energy infrastructure.

View jobs by Crusoe, Inc.

Skills

C#Cuda Docker Gpu Inference Kubernetes Llm Ml Optimization Profiling Python Sglang Vllm

Candidate Availability

Onsite · San Francisco · Required

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will optimize large language model inference systems for production, from profiling latency, throughput, and cost through kernel-level serving improvements. You will tailor deployments to customer constraints, take proofs of concept into monitored services, and deliver well-tested performance improvements.

Requirements

Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field
Experience shipping production code in Python, C++, or another general-purpose language
Knowledge of high-throughput, low-latency LLM inference optimization
Experience with LLM serving frameworks such as vLLM or SGLang
Ability to profile performance at the kernel level
Understanding of GPU architecture
Experience with large language models and AI/ML pipelines
Ability to communicate complex technical topics to customers and teammates

Responsibilities

Implement and refine inference optimization techniques in production
Design and optimize serving architectures, including prefill and decode disaggregation and request routing
Profile serving frameworks and CUDA kernels to identify and resolve performance issues
Tune deployments for latency, throughput, cost, and reliability
Tailor customer deployments and move workloads from proof of concept to monitored production services
Build production software and product features around the inference stack
Develop specifications, proofs of concept, and well-tested solutions
Own delivery from experimentation through production optimization
Draft features and product requirements with engineering and product stakeholders

Benefits

Restricted Stock Units
Paid time off, paid holidays, and leave of absence programs
Health, dental, and vision insurance
Employer HSA contributions
Paid parental leave
Paid life insurance and short-term and long-term disability coverage
Tuition reimbursement
Mental health and wellness support
Commuter benefits
Cell phone stipend
401(k) plan with company match up to 4% of salary
Volunteer time off
Global travel insurance and emergency assistance
Daily meals allowance