2 months ago
Base Salary
$215k - $260k/yr
Responsibilities
- Bring modern inference optimization techniques into production.
- Design and optimize serving architectures, including prefill and decode disaggregation and request routing.
- Profile and improve serving frameworks such as vLLM and SGLang, including underlying CUDA kernels.
- Adapt optimization methods across ML models, particularly large language models.
- Tune deployments for latency, throughput, cost, and reliability under real traffic.
- Partner with customer engineering teams to move workloads from proof of concept to monitored production services.
- Build and support production software and product features around the inference stack, preferably in Python.
- Define specifications, run focused experiments, and ship well-tested optimization results.
- Own delivery from initial experimentation through production deployment and help draft product requirement documents.
Requirements
- Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
- Hands-on experience shipping production code in a general-purpose language such as Python or C++, with a strong preference for Python.
- Experience with techniques for optimizing LLMs for high-throughput and low-latency inference.
- Familiarity with LLM serving frameworks such as vLLM or SGLang and with kernel-level performance profiling and analysis.
- Strong understanding of GPU architecture and behavior.
- Hands-on experience and clear interest in large language models.
- Working knowledge of AI/ML pipelines and the full model development and deployment lifecycle.
- Strong communication skills for explaining complex technical topics to customers and teammates.
- Preferred qualifications include software performance optimization experience, CUDA or comparable technology experience, strong software engineering fundamentals, AI/ML inference-system experience, Docker and Kubernetes experience, and customer-facing AI/ML project experience.
Benefits
- Competitive compensation and equity packages, including Restricted Stock Units.
- Paid time off, paid holidays, leave programs, and paid parental leave.
- Comprehensive health, dental, and vision insurance.
- Employer HSA contributions, paid life insurance, and short- and long-term disability coverage.
- Professional development, tuition reimbursement, and mental health and wellness support.
- Commuter benefits, cell phone stipend, 401(k) plan with company match up to 4% of salary, and volunteer time off.
- Global travel insurance, emergency assistance, daily meals allowance, and location-specific perks.
Tech Stack
Categories
About Crusoe
Crusoe builds and operates GPU-powered data centers and an AI cloud platform for enterprises running large-scale AI training and inference. It vertically integrates energy supply with compute, using stranded and renewable power to reduce emissions and costs, and sells capacity via cloud services and managed infrastructure. Founded in 2018 and headquartered in Denver, the company is privately held.