2 days ago
Base Salary
$182k - $242k/yr
Responsibilities
- Lead design reviews, architecture, and decomposition of multi-service initiatives.
- Define and own SLIs/SLOs and ensure post-incident actions improve reliability.
- Implement inference optimizations including micro-batch schedulers, speculative decoding, and KV-cache reuse.
- Improve capacity planning, autoscaling, graceful degradation, rollback, and traffic-shifting strategies.
- Mentor IC1/IC2 engineers and review cross-team designs and coding/testing standards.
- Own an area spanning multiple services and teams at the IC4 level.
- Improve P95/P99 latency, throughput, reliability, and cost through metrics-driven engineering.
Requirements
- 3–5 years of industry experience for IC3 or 5–8 years for IC4 building distributed systems or cloud services.
- Strong coding skills in Python or Go; C++ is a plus.
- Deep familiarity with networked systems, performance, production-scale Kubernetes, CI/CD, and observability stacks.
- Practical knowledge of inference internals including batching, caching, mixed precision, and streaming token delivery.
- Proven experience improving tail latency and service reliability through metrics-driven work.
- Bachelor’s or Master’s degree in Computer Science or a related field, or equivalent practical experience.
- Preferred: contributions to vLLM, Triton, TensorRT-LLM, Ray Serve, or TorchServe.
- Preferred: experience with CUDA kernels, NCCL/SHARP, RDMA/NUMA, GPU interconnect topologies, multi-team initiatives, or mission-critical customer launches.
Benefits
- $182,000–$242,000 base salary, plus discretionary bonus and equity awards.
- Medical, dental, and vision insurance fully paid by CoreWeave for eligible US-based full-time employees.
- Company-paid life insurance, supplemental life insurance, short- and long-term disability insurance, FSA, and HSA.
- Tuition reimbursement and eligibility for the employee stock purchase program.
- Mental wellness benefits through Spring Health and family-forming support through Carrot.
- Paid parental leave and flexible full-service childcare support through Kinside.
- 401(k) with employer match and flexible PTO.
- Catered lunch at office and data center locations, a casual work environment, and an innovation-focused culture.
Tech Stack
Categories
About CoreWeave
CoreWeave provides a GPU-accelerated cloud for AI training and inference, VFX, and rendering, with bare-metal instances, Kubernetes orchestration, and managed services to scale workloads. It sells on-demand and reserved capacity to AI labs, startups, and enterprises, and offers SaaS tools and hands-on support for deployment. Founded in 2017 and headquartered in New York, it is publicly traded on Nasdaq under the ticker CRWV.