
Staff Software Engineer – Performance and Benchmarking
Posted 7 hours ago

Posted 7 hours ago
This is a fully remote position, open to applicants in United States.
• Design and improve Kubernetes-native benchmarking services that evaluate latency, throughput, jitter, and cost-per-request throughout CoreWeave’s compute stack.
• Develop and sustain benchmarking workflows for comprehensive MLPerf Training and Inference runs, encompassing workload setup, cluster configuration, and result validation.
• Engage in design conversations and contribute to architectural choices.
• Decompose engineering tasks into distinct milestones and deliver dependable, high-quality code.
• Collaborate with colleagues to uphold reproducible and well-documented benchmarking procedures.
• Offer constructive code reviews and disseminate best practices.
• Mentor junior engineers; assess cross-team designs and enhance coding/testing standards.
• Ingest, store, transform, and analyze performance events across international data centers.
• Support leading-edge end-to-end performance benchmarking publications like MLPerf.
• 3–5 years of experience in developing distributed systems, high-performance computing components, or cloud services.
• Proficient programming skills in Python or Go (C++ is advantageous) with a solid grasp of networked systems and performance principles.
• Practical experience with Kubernetes in production settings along with familiarity with CI/CD and observability tools (e.g., Prometheus, Grafana, OpenTelemetry).
• Knowledge of performance-critical GPU systems (CUDA, NCCL, NVLink/PCIe, memory bandwidth) or model-serving stacks (llm-d, vLLM, TensorRT-LLM, Megatron-LM).
• Strong communicator comfortable working across various functions.
• Experience with time-series databases, LSM-based storage engines, or custom data pipelines.
• Familiarity with MLPerf or other extensive benchmarking frameworks.
• Contributions to open-source projects such as llm-d, vLLM, or PyTorch.
• Exposure to benchmarking GPU clusters or multi-region environments.
• Background in working with CUDA kernels, NCCL/SHARP, RDMA/NUMA, or GPU interconnect architectures.
• Discretionary bonus
• Equity awards
• Medical, dental, and vision insurance - 100% covered by CoreWeave
• Company-paid Life Insurance
• Voluntary supplemental life insurance
• Short and long-term disability insurance
• Flexible Spending Account
• Health Savings Account
• Tuition Reimbursement
• Opportunity to take part in Employee Stock Purchase Program (ESPP)
• Mental Wellness Benefits through Spring Health
• Family-Forming support provided by Carrot
• Paid Parental Leave
• Flexible, full-service childcare support with Kinside
• 401(k) with a generous employer match
• Flexible PTO
• Daily catered lunch in our office and data center locations
• A relaxed work environment
• A work culture centered on innovative disruption
Helpware
Introhive
Boeing
M9 Solutions
Get handpicked remote jobs straight to your inbox weekly.