Staff Applied AI Inference Engineer
Crusoe · San Francisco, CA - US
Infrastructureonsitestaff$215k–$260k
At a glance
Highlights
- Make large language models run faster, cheaper and more reliably in production.
- Own the inference stack end to end from profiling to production deployment.
- Design serving architectures including prefill and decode disaggregation.
What they offer
- Restricted Stock Units
- Comprehensive health, dental and vision insurance
- Paid time off, holidays and leave programs
- 401(k) with company match up to 4%
- Paid parental leave
- Professional development and tuition reimbursement
- Daily meals allowance
Ideal candidate
Hands-on systems thinker who loves squeezing performance from demanding workloads and thrives in ambiguity. You enjoy partnering directly with customers to turn fuzzy goals into reliable production systems.
Requirements
- Firm grasp of GPU architecture and behavior
- Hands-on experience with large language models
- Working knowledge of AI/ML pipelines and model deployment
- Proficiency in Python or other general-purpose languages
- Strong communication skills for customer-facing technical work
Lab profile
About Crusoe
Vertically integrated AI infrastructure company powering ambitious AI workloads from electrons to tokens.
What they build
- Crusoe Cloud for AI workloads
- Purpose-built AI data centers
- Managed GPU infrastructure
Known for
- Vertically integrated from electrons to tokens
- Owns and operates full infrastructure stack
- Built for large-scale AI workloads
Key facts
- Founded in 2018
- Headquartered in San Francisco, CA
Posted · Last seen