Senior AI Systems Engineer — Scalable Model Serving

Apply; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 210,000; Full time

Job summary

Perplexity AI seeks a deeply technical software engineer to own and evolve its model serving platform, connecting our products and research systems with inference layers. This mission-critical service sits at the intersection of distributed systems, AI products, and infrastructure, enabling teams to adopt new models and ship reliable products.

You will design core abstractions, drive high-conviction technical decisions, and write production Rust and Python for a service handling hundreds of

Qualifications

• 5+ years building large-scale, reliable systems.
• Strong craft with focus on developer experience.
• Proficiency in Python, Rust, C++, or Go and cloud infra (AWS, Kubernetes).
• BS, MS or PhD in CS/Engineering or related field or equivalent experience.

Responsibilities

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

Skills

Distributed systems

Production-grade software

Backend development

System reliability

Education

BS/MS/PhD in CS or related field

Tools

Python

Rust

C++

Go

AWS

Kubernetes

Job description

Perplexity AI seeks a deeply technical software engineer to own and evolve its model serving platform, connecting our products and research systems with inference layers. This mission-critical service sits at the intersection of distributed systems, AI products, and infrastructure, enabling teams to adopt new models and ship reliable products.

You will design core abstractions, drive high-conviction technical decisions, and write production Rust and Python for a service handling hundreds of