Staff Software Engineer, AI Model Serving & Infra

United States Digital Space LLC; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Perplexity is seeking a deeply technical software engineer to own and evolve our model serving platform, connecting products and research systems with our inference layers. This mission-critical system provides teams one fast, reliable interface across providers.

You will work at the intersection of distributed systems, AI products, and infrastructure, enabling teams to adopt new models, run experiments, and ship dependable products with production Rust and Python.

Qualifications

• 5+ years of experience building and shipping large-scale systems
• Strong software engineering craft with focus on developer experience
• Proficiency with backend languages (Python, Rust, C++, Go) and cloud infra (AWS, Kubernetes)
• BS, MS, or PhD in Computer Science, Engineering, or related fields (or equivalent)

Responsibilities

• Own and evolve the model serving platform and inference interface
• Connect products and research systems with inference layers
• Design core abstractions and drive high-conviction technical decisions
• Write production Rust and Python for a service handling hundreds of millions of model requests daily

Skills

Backend development

Distributed systems

Rust

Python

C++

Go

AWS

Kubernetes

Education

BS/MS/PhD in CS/Engineering

Job description

Perplexity is seeking a deeply technical software engineer to own and evolve our model serving platform, connecting products and research systems with our inference layers. This mission-critical system provides teams one fast, reliable interface across providers.

You will work at the intersection of distributed systems, AI products, and infrastructure, enabling teams to adopt new models, run experiments, and ship dependable products with production Rust and Python.