Braintrust is the AI observability platform. By connecting evals and observability in one workflow, Braintrust gives builders the visibility to understand how AI behaves in production and the tools to improve it.
Teams at Notion, Stripe, Zapier, Vercel, and Ramp use Braintrust to compare models, test prompts, and catch regressions — turning production data into better AI with every release.
About the RoleWe’re hiring engineers to build the open-source libraries that customers use to observe, understand, and optimize how AI operates inside their production applications. These SDKs are a critical part of Braintrust’s platform. They power evaluation and observability pipelines across a wide range of environments, frameworks, and AI providers.
This role is ideal for engineers who are passionate about developer experience, API craftsmanship, and building fast, reliable, and idiomatic libraries. You’ll own the full SDK lifecycle: design, implementation, release, documentation, and community support. Your work will be embedded in thousands of applications and help define how AI is adopted and operationalized across industries.
What You’ll DoBuild elegant, idiomatic, and resilient SDKs that power Braintrust’s LLM evaluation and AI observability platform.
Ensure our libraries are easy to use, efficient to run, and a delight to work with, prioritizing developer experience and performance.
Integrate with major AI providers, frameworks, and platforms our customers rely on, such as OpenAI, Anthropic, and Gemini.
Build tools and automation to improve testing, profiling and simplify release workflows.
Collaborate closely with backend, platform, and product teams to ensure a cohesive and polished developer experience.
Be a great community ambassador: talk with our users, understand their issues, help them get their fixes merged and have deep empathy for our users.
Are customer-obsessed and passionate about solving real-world problems for developers.
Have deep expertise in Python and understand what it takes to build fast, idiomatic, and reliable libraries in that ecosystem.
Are proficient with the tooling needed to build robust SDKs, such as testing frameworks, profilers, CI/CD pipelines, and packaging systems.
Care deeply about developer experience, from clean APIs and clear docs to thoughtful error handling and backward compatibility.
Know how to wrap, patch, or extend existing frameworks and SDKs to inject observability and control without breaking developer workflows.
Have experience maintaining or contributing to production-grade open-source libraries, ideally used across multiple environments.
Bonus: You’ve contributed to popular open source projects, led SDK adoption at your organization, are familiar with tracing and observability tools like OpenTelemetry, or worked on tools in the LLM/AI ecosystem.
Medical, dental, and vision insurance
Daily lunch, snacks, and beverages
Flexible time off
Competitive salary and equity
AI Stipend
Braintrust is an equal opportunity employer. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.
What We Do
Braintrust is an AI-native observability platform that helps teams measure, evaluate, and improve AI models and products in production.
