Eval Engineer

Braintrust•San Francisco, CA

12d

About The Position

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 role We’re hiring an Eval Engineer to design and run creative evaluations of new AI capabilities. Your job is to turn emerging AI ideas into measurable experiments and publish the results for the developer ecosystem. When new models, agents, or frameworks appear, everyone has opinions about what works but few people actually test them. This role exists to change that. You’ll design experiments that compare models, prompts, and agent architectures against real tasks. You’ll build the datasets, scoring logic, and evaluation harnesses. Then you’ll publish the results so builders understand what actually works. This role sits at the intersection of engineering, experimentation, and technical storytelling.

Requirements

You’re an engineer who likes testing systems more than building features
You enjoy breaking things and understanding why they fail
You can design experiments that isolate meaningful differences between approaches
You understand how LLMs, agents, and RAG systems actually work
You write clearly for technical audiences
You ship experiments quickly and iterate often
You care about methodology and reproducibility
You’re curious, creative, and opinionated about how AI should be evaluated

Nice To Haves

Built or contributed to evaluation systems for LLM or agent applications
Designed experiments comparing models, prompts, or AI architectures
Written Python code to run tests across models or APIs
Built datasets or scoring logic for AI quality measurement
Investigated model failures or unexpected behaviors
Published technical blog posts, research notes, or engineering write-ups
Built prototypes quickly to test ideas

Responsibilities

Industry evals Design and run evaluations of new AI capabilities Compare frontier models, agent systems, and tool workflows Turn emerging ideas into measurable benchmarks
Eval design Define datasets, tasks, and scoring logic for experiments Design realistic workloads that reflect production environments Create tests that expose failure modes and edge cases
Experiment implementation Build evaluation harnesses using Braintrust Run comparisons across models, prompts, and agent approaches Analyze traces, outputs, and failure patterns
Creative test construction Invent novel ways to stress test AI systems Design scenarios that break agents, prompts, and model reasoning Build adversarial or complex datasets that reveal weaknesses
Technical content Write technical posts explaining evaluation methodology and results Share datasets and scoring logic so experiments are reproducible Help establish better evaluation patterns for the industry via courses
Evaluation playbooks Develop reusable eval patterns for agents, RAG systems, and LLM apps Create open source reference implementations developers can adopt Contribute examples and guides that help teams build better evals