SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Snowflake is seeking a Principal Software Engineer to lead the Capacity, Performance & Efficiency team's cloud infrastructure performance strategy. This high-autonomy role sits at the intersection of cloud hardware, workload behavior, performance measurement, and business economics, driving Snowflake's hardware adoption strategy, price/performance decisions, and platform footprint expansion.
You will own evaluation and enablement of new hardware generations across AWS, Azure, and GCP (e.g., Graviton, AMD Turin, Azure Cobalt, GCP Axion). You'll build benchmarking and modeling infrastructure that translates raw performance data into pricing and rollout decisions, and represent Snowflake in technical discussions with cloud service providers and silicon partners.
Key responsibilities include: leading new hardware evaluation by building representative benchmarks; shaping the team's technical roadmap and measurement methodology; translating benchmark results into concrete adoption recommendations; analyzing CPU microarchitecture, memory bandwidth, and I/O behavior to identify workload-specific bottlenecks; developing price/performance models for hardware transitions; automating day-zero hardware readiness with validation workflows and per-provider scorecards; and growing performance engineering as a discipline by mentoring engineers, building benchmarking capability, and driving company-wide performance education.
You'll work cross-functionally with engineering teams (Warehouse, Capacity, core platform), Finance, and external partners at AWS, Azure, and GCP to qualify new hardware and influence future cloud-instance designs.
Required: 12+ years in performance engineering, systems engineering, or infrastructure engineering with principal-level technical leadership. Deep expertise in cloud infrastructure performance across at least one major CSP, including instance types, pricing models, and capacity constraints. Strong grounding in hardware/systems fundamentals: CPU microarchitecture, memory bandwidth, I/O subsystems, and profiling tools (PMU counters). Experience building or operating large-scale benchmarking systems and turning benchmark output into actionable pricing/rollout decisions. Ability to build quantitative models connecting technical metrics to business outcomes. Track record of leading cross-functional, cross-company initiatives and serving as primary technical point of contact with external partners. Bias toward automation and building scorecards, dashboards, and validation pipelines.
Nice to have: data warehouse/distributed database performance experience; direct experience with cloud provider or silicon vendor early-access programs; hardware-emulation systems experience.
