Senior Inference Systems Performance Architect

SambaNova, Inc.; San Jose (CA); On-site; USD 245,000 - 325,000; Full time

Benefits offered by this job

Health insurance

Equity and benefits

Health Savings Account (HSA)

Job summary

SambaNova Systems in San Jose, CA seeks a senior leader to architect end-to-end inference performance, from tokenization to decode, across heterogeneous hardware. You will model workloads, simulate configurations, and drive capacity planning to meet customer SLOs.

You will guide benchmarking, work with model-optimization, systems, and hardware teams, and mentor engineers while shaping the technical direction for future AI inference platforms.

Qualifications

• B.S. in Computer Science, Computer Engineering, or Related Field.
• 12+ years of experience in performance engineering.
• Deep expertise in end-to-end performance analysis of distributed systems.
• Proven ability to model and simulate workloads and calibrate against real data.
• Leadership across cross-functional teams and influence on roadmap.
• Experience representing an organization credibly to customers/partners.
• Track record delivering high-complexity, high-ambiguity work with impact.

Responsibilities

• Define and drive inference-systems performance strategy across workload capture, benchmarking, modeling, and simulation.
• Build workload-capture and agentic-benchmarking capability with representative production traffic.
• Own performance-modeling and simulation to inform capacity planning and hardware directions.
• Address end-to-end profiling gaps across host, accelerator, and fabric in a distributed pipeline.
• Serve as senior technical voice across model optimization, systems, hardware, and product.
• Mentor senior engineers and raise organizational capability in tooling and patterns.
• Drive resolution of ambiguous, novel challenges spanning organizational boundaries.

Skills

Performance engineering

Distributed systems

Workload generation

Performance modeling

Leadership

Cross-functional collaboration

Education

Bachelor's degree in CS/CE or related field

MS/PhD in CS/CE (preferred)

Tools

LLM inference serving

Inference simulation frameworks

Agentic benchmarking

Job description

SambaNova Systems in San Jose, CA seeks a senior leader to architect end-to-end inference performance, from tokenization to decode, across heterogeneous hardware. You will model workloads, simulate configurations, and drive capacity planning to meet customer SLOs.

You will guide benchmarking, work with model-optimization, systems, and hardware teams, and mentor engineers while shaping the technical direction for future AI inference platforms.