2 months ago
Base Salary
$215k - $260k/yr
Responsibilities
- Bring modern LLM inference optimization techniques into production.
- Design and optimize serving architectures, including prefill and decode disaggregation and request routing.
- Profile and improve serving systems from frameworks such as vLLM and SGLang down to CUDA kernels.
- Adapt optimization methods across ML models, especially large language models.
- Tune deployments for latency, throughput, cost, and reliability under real traffic.
- Partner with customer engineering teams to take workloads from proof of concept through monitored production deployment.
- Build and support production software and product features around the inference stack, primarily using Python.
- Define specifications, run focused experiments and proofs of concept, and ship tested optimizations.
- Own delivery from initial experimentation through production implementation and collaborate on features and product requirement documents.
- Make pragmatic tradeoffs around tooling and system complexity.
Requirements
- Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
- Production software development experience with one or more general-purpose languages such as Python or C++, with Python preferred.
- Hands-on familiarity with techniques for optimizing LLMs for high-throughput and low-latency inference.
- Experience with LLM serving frameworks such as vLLM or SGLang and with kernel-level profiling and performance analysis.
- Strong understanding of GPU architecture and behavior.
- Clear interest in and hands-on experience with large language models.
- Working knowledge of AI/ML pipelines and the development and deployment lifecycle for ML models.
- Strong communication skills for explaining complex technical topics to customers and teammates.
- Preferred experience includes accelerating software systems, especially LLM systems, and building and shipping AI/ML inference systems.
- Preferred experience includes CUDA or comparable technologies, Docker, Kubernetes, and customer-facing AI/ML projects.
Benefits
- Competitive compensation and equity packages, including Restricted Stock Units.
- Paid time off, paid holidays, and leave of absence programs.
- Comprehensive health, dental, and vision insurance.
- Employer HSA contributions.
- Paid parental leave.
- Paid life insurance and short- and long-term disability coverage.
- Professional development and tuition reimbursement.
- Mental health and wellness support.
- Commuter benefits for parking and transit.
- Cell phone stipend.
- 401(k) retirement plan with company match up to 4% of salary.
- Volunteer time off.
- Global travel insurance and emergency assistance.
- Daily meals allowance and additional location-specific perks and programs.
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.