Product Platform: Backend Engineer

present of AI; San Francisco (CA); On-site; USD 140,000 - 200,000; Full time

Job summary

Baseten is seeking a backend engineer to join our inference platform team. You’ll build services and APIs that power our customers and internal teams, with emphasis on reliability, data flow, and clear interfaces.

You’ll work near deployment and model serving paths, focusing on performance and correctness under load, and gain hands-on exposure to deploying AI models at scale and the APIs that surround them.

Qualifications

• Experience with server-side languages, databases and API design.
• Focus on reliability, data flow and clear interfaces.
• Understanding of distributed systems and performance under load.

Responsibilities

• Build backend services and APIs powering the platform and customers.
• Ensure reliability, scalability and proper data flow across services.
• Collaborate with infra and product teams to design robust interfaces.

Skills

Backend service development

API design

Database design

Distributed systems basics

Performance & reliability

Job description

Backend engineers on a product platform team typically build the services and APIs that other teams and customers rely on, with attention to reliability, data flow and clear interfaces. A strong candidate brings solid experience in server side languages, database and API design, and comfort working close to infrastructure. At a company serving AI models in the cloud, that work likely touches deployment, scaling and model serving paths, so care with performance and correctness matters.

How it fits the AI era

Backend work on an inference platform sits close to where AI meets real traffic, so the role grows more central as more teams run models in production. AI tools speed up routine coding and testing, but judgment about system design, failure modes and tradeoffs stays with the engineer. The human part is deciding what to build and making it dependable under load.

How it builds AI experience

This role offers hands on exposure to how AI models are deployed and served at scale, including the infrastructure and APIs around them. That experience is built by working on serving paths, capacity and reliability problems rather than by training models. Someone wanting this kind of work can strengthen it with projects that run and scale a model behind an API.

Worth showing

• Backend service development
• API and database design
• Distributed systems basics
• Performance and reliability work

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About Baseten

High-performance cloud inference platform for deploying, serving, and scaling open-source and custom artificial intelligence models.