Latest AI JobsBrowse Jobs
Crusoe logo

Senior Staff Applied AI Inference Engineer

CrusoeSan Francisco, CA - USCloud Engineering
Apply on company site
Salary
$250K - $300K
Job type
Full-time
Experience
Senior
Posted
22 Sept 2026
Status
Open · checked 7d ago

About this role

Crusoe is seeking a Senior Staff Applied AI Inference Engineer in San Francisco, CA, to own the end-to-end inference stack and optimize large language models for production. This hands-on, customer-facing role suits an experienced engineer with a background in low-level performance tuning, GPU behavior, and LLM serving architectures.

Role Overview

Crusoe operates as a vertically integrated AI infrastructure company, managing the stack from power generation to AI tokens. The Senior Staff Applied AI Inference Engineer spends time making large language models run faster, cheaper, and more reliably in production. This position combines core systems engineering, performance profiling, and customer collaboration to take workloads from initial proofs of concept to fully monitored production services.

Key Responsibilities

Implement and refine modern inference techniques for production deployments.
Design and optimize serving architectures including request routing, prefill and decode disaggregation, and related approaches.
Profile performance down to the CUDA kernel level using frameworks like vLLM and SGLang.
Adapt and scale optimization methods across various machine learning models with a primary focus on large language models.
Tune deployments to meet specific targets for latency, throughput, and cost under real traffic conditions.
Partner with customer engineering teams to tailor deployments and move workloads from prototypes to live production services.
Build software and product features around the inference stack using general-purpose languages, preferring Python.
Translate ambiguous goals into clear specifications, proofs of concept, and tested shipping results.
Own end-to-end delivery of optimizations while drafting feature and product requirements alongside engineering and product teams.

Requirements

Hold a Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
Possess hands-on experience shipping production code using general-purpose languages like Python or C++, with a strong preference for Python.
Demonstrate familiarity with methods for optimizing large language models for high throughput and low latency.
Show comfort with modern serving frameworks such as vLLM or SGLang, alongside kernel-level profiling and performance analysis.
Maintain a firm understanding of GPU architecture and behavior.
Bring practical experience and interest in large language models.
Possess working knowledge of AI and machine learning pipelines from development to deployment.
Exhibit strong communication skills for explaining complex technical topics to customers and teammates.

Nice to Have

A track record of accelerating software systems, particularly for large language models.
Experience working with CUDA or comparable technologies.
Strong software engineering fundamentals with a history of building and shipping AI and ML inference systems.
Experience utilizing Docker and Kubernetes.
Prior background in customer-facing AI or ML project tuning and building.

Skills and Tools

Python
C++
vLLM
SGLang
CUDA
Docker
Kubernetes
Large Language Models

Salary and Benefits

Compensation range of $250,000 to $300,000 plus bonus
Restricted Stock Units included in all offers
Comprehensive health, dental, and vision insurance with employer HSA contributions
401(k) retirement plan with company match up to 4% of salary
Paid time off, paid holidays, leave of absence programs, and paid parental leave
Paid life insurance, short-term and long-term disability
Professional development and tuition reimbursement
Mental health and wellness support, commuter benefits, and daily meals allowance
Cell phone stipend, volunteer time off, and global travel insurance with emergency assistance

About the Company

Crusoe operates as a vertically integrated AI infrastructure company building out energy and intelligence capabilities from the ground up. The organization owns and operates every layer of the stack to support demanding AI workloads with an energy-first approach.

How to Apply

Candidates should apply directly on the official company careers page.

Skills and tech stack

PythonC++vLLMSGLangCUDADockerKubernetesLLMLLMs

Questions candidates ask

What is the salary range for the Senior Staff Applied AI Inference Engineer role?

The compensation range is $250,000 to $300,000 plus a bonus, and all offers include Restricted Stock Units.

Where is the position located?

The role is located in San Francisco, CA - US.

What programming languages are required or preferred?

Experience shipping code in general-purpose languages such as Python or C++ is required, with a strong preference for Python.

What inference frameworks and tools are mentioned in the posting?

The posting notes familiarity with vLLM, SGLang, CUDA, Docker, and Kubernetes.

What educational background is expected?

Candidates must hold a Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.

Ready to apply?

The application is on the official Crusoe careers page.

Apply on company site