AI Platform Engineer for Developer Productivity

Baseten; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Equity

Medical, dental, vision

Flexible PTO

Parental leave

401(k)

Learning opportunities

Job summary

Baseten is building an AI-focused platform engineering team in San Francisco to create a scalable, self-service environment for AI-native SDLC across internal agents and tooling. You’ll shape the platform, evaluation, and rollout, enabling engineers to ship safe, productive AI-powered solutions.

You’ll work on agent configurations, MCP, context management, and tooling to empower teams while measuring impact on velocity and reliability.

Qualifications

• 4+ years of experience building and enabling AI native SDLC.
• Proficiency in Python and/or Go; building tools daily.
• Hands-on experience with LLMs and agent frameworks—tool calling and context management.
• Fluency with AI coding tools and strong opinions on their limits.
• Platform mindset: self-service, adoptable defaults, engineers as customers.
• CI/CD, and Kubernetes/Docker fundamentals.
• Comfort with ambiguity and evolving best practices.
• Excellent written communication for docs and templates.

Responsibilities

• Own the internal AI developer platform end to end—architecture, build, rollout, operation, measurement.
• Evaluate and integrate third-party AI coding tools and build the context layer to work with our monorepo.
• Build frameworks for engineers to create their own agents without deep LLM expertise.
• Establish evaluation practices for AI-assisted development to inform investments.
• Drive adoption through developer experience with clear docs and low friction.
• Collaborate with teams to generalize wins into platform capabilities.
• Own the safety layer: permissions, secrets handling, audit trails, cost management.

Skills

Python

Go

LLMs

Agent frameworks

CI/CD

Kubernetes

Docker

Developer tooling

Platform mindset

Documentation

Tools

Kubernetes

Docker

Job description

Baseten is building an AI-focused platform engineering team in San Francisco to create a scalable, self-service environment for AI-native SDLC across internal agents and tooling. You’ll shape the platform, evaluation, and rollout, enabling engineers to ship safe, productive AI-powered solutions.

You’ll work on agent configurations, MCP, context management, and tooling to empower teams while measuring impact on velocity and reliability.