Partner Platform Engineer – API & Infra for AI in Production

Xapply; San Francisco (CA); On-site; USD 210,000 - 290,000; Full time

Benefits offered by this job

Competitive compensation + equity

100% medical, dental, vision (US) for

Winter Break PTO

Paid parental leave

Fertility and family-building stipend

401(k) plan

Job summary

Baseten, based in San Francisco, builds an inference platform enabling AI models to run in production. We seek a Partner Engineer to own strategic integrations with model labs, hyperscalers, and developer platforms, turning partnerships into tangible products.

You will collaborate with partner teams and Baseten engineers to deliver reliable, scalable infrastructure and APIs. This role focuses on creating reusable primitives across identity, provisioning, inference, model serving, metering, and

Qualifications

• Experience designing, shipping, and operating large-scale distributed systems in production.
• Ability to lead ambiguous engineering projects across teams while contributing production code.
• Strong judgment on API design, service boundaries, and failure handling.
• Experience turning customer/partner requests into defined technical scope and documenting decisions.
• Comfort debugging across application code and cloud infrastructure.

Responsibilities

• Lead strategic partner integrations from technical discovery through implementation, launch, and production operation.
• Work with partner engineering teams to design APIs, define system boundaries, and resolve cross-company dependencies.
• Write substantial production code and own the systems you build.
• Build reusable partner-platform primitives across identity, provisioning, inference, model serving, metering, and billing.
• Own technical delivery across Baseten and partner teams, including milestones, risks, and tradeoffs.
• Collaborate with Partnerships and Product to translate ecosystem opportunities into platform investments.
• Raise the bar for integration reliability via strong API contracts, testing, and safe rollouts.

Skills

Large-scale distributed systems

Cross-team leadership

API design

Requirements gathering

Cloud/infrastructure debugging

Cloud integrations

Usage metering

Model serving

Job description

Baseten, based in San Francisco, builds an inference platform enabling AI models to run in production. We seek a Partner Engineer to own strategic integrations with model labs, hyperscalers, and developer platforms, turning partnerships into tangible products.

You will collaborate with partner teams and Baseten engineers to deliver reliable, scalable infrastructure and APIs. This role focuses on creating reusable primitives across identity, provisioning, inference, model serving, metering, and