Latest AI JobsBrowse Jobs
Crusoe logo

Staff Applied AI Inference Engineer

CrusoeSan Francisco, CA - USCloud Engineering
Apply on company site
Salary
$215K - $260K
Job type
Full-time
Experience
Senior
Posted
8 Sept 2026
Status
Open · checked 7d ago

About this role

San Francisco, CA offers a Staff Applied AI Inference Engineer role at Crusoe focusing on performance optimization for large language models. This position suits an experienced systems engineer who enjoys hands-on optimization, profiling, and working directly with customer engineering teams.

Role Overview

Crusoe seeks a Staff Applied AI Inference Engineer to make large language models execute faster, cheaper, and more reliably in production environments. The job involves owning the inference stack from end to end, profiling performance bottlenecks, bringing modern optimization methods into real deployments, and collaborating with customers to meet latency, throughput, and cost targets.

Key Responsibilities

Integrate and refine current inference techniques into production environments.
Architect and optimize serving systems, including request routing, prefill, and decode disaggregation.
Profile serving stacks from frameworks down to CUDA kernels to identify and resolve performance constraints.
Scale optimization approaches across various machine learning models with a primary focus on large language models.
Tune production deployments against strict latency, throughput, and cost parameters under real traffic conditions.
Partner with customer engineering teams to adapt deployments to specific requirements and transition workloads from proofs of concept to monitored production services.
Write production software and build product features using general-purpose languages such as Python.
Translate ambiguous goals into clear specifications, fast experiments, and well-tested outcomes.
Manage end-to-end delivery of optimizations while collaborating with product and engineering teams on requirements.

Requirements

Hold a Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
Bring practical experience shipping production code using general-purpose languages like Python or C++, with a strong preference for Python.
Possess familiarity with methods designed to optimize large language models for low latency and high throughput.
Show comfort with serving frameworks such as vLLM or SGLang, along with profiling capabilities down to the kernel level.
Understand GPU architecture and behavior thoroughly.
Demonstrate hands-on experience and interest in large language models alongside working knowledge of machine learning pipelines.
Display strong communication skills for explaining complex technical topics to customers and teammates.

Nice to Have

Proven history of accelerating software systems, specifically for large language models.
Experience utilizing CUDA or similar technologies.
Strong software engineering fundamentals paired with a background in building AI inference systems.
Familiarity with Docker and Kubernetes.
Previous experience building or tuning machine learning projects in customer-facing roles.

Skills and Tools

Python
C++
vLLM
SGLang
CUDA
Docker
Kubernetes
GPUs

Salary and Benefits

The salary range spans from $215,000 to $260,000 plus bonus, with Restricted Stock Units included in all offers. Benefits comprise comprehensive health, dental, and vision insurance, employer HSA contributions, 401(k) matching up to 4%, paid time off, paid parental leave, life and disability insurance, professional development reimbursement, commuter benefits, a cell phone stipend, daily meal allowances, wellness support, and volunteer time off.

About the Company

Crusoe operates as a vertically integrated artificial intelligence infrastructure company built from the ground up to own and operate each layer of the energy-to-token stack. The organization takes an energy-first approach to address the boundless demand for AI compute and power bottlenecks.

How to Apply

Interested candidates should apply on the official company careers page.

Skills and tech stack

PythonC++vLLMSGLangCUDADockerKubernetesLLMLLMs

Questions candidates ask

What is the salary range for this role?

The compensation ranges from $215,000 to $260,000 plus a bonus, and all offers include Restricted Stock Units.

Where is the position located?

The job is located in San Francisco, CA.

What programming languages are required or preferred?

Hands-on production coding experience with general-purpose languages like Python or C++ is required, with a strong preference for Python.

What serving frameworks should candidates be familiar with?

Candidates should be comfortable with modern large language model serving frameworks such as vLLM or SGLang.

What educational qualifications are needed?

A Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field is required.

Ready to apply?

The application is on the official Crusoe careers page.

Apply on company site