Hands-on engineering role moving between experiments, benchmarks, and product code.
Help developers understand agents' behavior, evaluate performance, and improve over time.

Why:

Building agentic features into Mastra like Trace intelligence and Agent Learning.
Running Mastra primitives on industry-standard benchmarks to fine-tune configuration.

What you'll do:

Build tools for understanding traces, evaluating agent behavior, and turning results into improvements.
Run experiments on Mastra's primitives and use findings to improve their configuration and behavior.

About Mastra:

Open-source TypeScript framework for building AI agents.
Small team, fully remote, backed by Y Combinator and Spark Capital with $35M raised.

Mastra

Mastra is the open-source TypeScript framework for building AI agents. We're a small, fully remote team backed by Y Combinator and Spark Capital with $35M raised.

Apply for This Position