Inference Systems Performance Architect

Responsibilities

• Define and drive the technical strategy for inference-systems performance across workload capture, benchmarking, modeling, and simulation.
• Build workload-capture and agentic-benchmarking capabilities that represent production traffic and identify artificial contention or misleading cache-hit rates.
• Own performance modeling and simulation practices to inform capacity planning, customer SLOs, and future systems and hardware planning.
• Develop profiling tools that accurately localize bottlenecks across distributed inference hosts, accelerators, and fabrics.
• Act as the senior technical voice across model optimization, systems, hardware, and product teams while evaluating reliability, scalability, operational cost, and adoption trade-offs.
• Represent SambaNova’s performance capabilities to customers and partners.
• Mentor principal and senior engineers and create systems, tools, and patterns that improve organizational productivity.
• Drive resolution of ambiguous, novel, cross-organizational performance challenges.

Requirements

• 12+ years of experience in performance engineering with a record of technical leadership on large-scale, complex systems.
• Deep expertise in end-to-end performance analysis of distributed systems and bottleneck localization.
• Proven expertise in realistic workload generation, simulation, and performance modeling calibrated against variable real-world workloads.
• Ability to apply transferable performance methods in unfamiliar domains.
• Ability to lead cross-functional efforts, mentor senior engineers, and influence organizational direction.
• Experience credibly representing an organization to customers and partners.
• Track record of independently scoping and delivering high-complexity, high-ambiguity work with significant product or roadmap impact.
• Preferred: direct experience with LLM inference serving, continuous batching, prompt/KV caching, prefill/decode disaggregation, and tail-latency SLOs.
• Preferred: familiarity with inference simulation frameworks or agentic benchmarking efforts.
• Preferred: public technical presence through talks, writing, or community participation on systems performance.

Benefits

• Base benefits include medical insurance with 95% employee premium coverage and 77% dependent premium coverage, plus an employer-contributed Health Savings Account.
• Dental, vision, short- and long-term disability, basic life, voluntary life, AD&D, and flexible spending account options are available.
• Well-being benefits include Headspace, Gympass+ with access to physical gyms, One Medical, counseling services, and an Employee Assistance Program.
• The role is a full-time position for US-based employment.