Staff Engineer - Customer-Facing AI Inference Infra

Simplify; San Francisco (CA); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Housing stipend

Uber/Waymo rides

Job summary

Simplify in San Francisco is hiring Members of Technical Staff to build systems that accelerate LLM inference and own customer workloads end to end. You will work on high-performance kernels, inference engine internals, and production infrastructure for named accounts.

You will own client relationships, be on-site in SF five days a week, and help drive technical evaluations with real workloads while collaborating with a fast-growing AI inference company.

Qualifications

• Shipped and operated production systems; on-call experience.
• Had a customer relationship or a deployment with real users.
• Credible in a room full of engineers; can defend a benchmark methodology.
• Able to work without a spec.
• In person in San Francisco, 5 days/week.
• Already in the US (they sponsor and transfer essentially any visa status).

Responsibilities

• Develop and optimize high-performance computing kernels and work across inference engine internals and serving infrastructure.
• Develop AI agents to do autonomous inference engineering.
• Design, deploy, and operate heterogeneous clusters across vendors.
• Own customer accounts end to end and maintain production for workloads.
• Explain benchmark results to customers' engineers and drive technical evaluations.
• Inform product roadmap with real-load observations from accounts.

Skills

Production systems

On-call debugging

Customer relationship

Benchmark methodology

In-person SF

Job description

Simplify in San Francisco is hiring Members of Technical Staff to build systems that accelerate LLM inference and own customer workloads end to end. You will work on high-performance kernels, inference engine internals, and production infrastructure for named accounts.

You will own client relationships, be on-site in SF five days a week, and help drive technical evaluations with real workloads while collaborating with a fast-growing AI inference company.