We help agent developers maintain and improve their ai software by identifying problems and fixing them with changes to scaffolding code, prompts, and models.

As a AI engineer, you’ll work across our stack to productionize, maintain, and scale our research engineering agent products and experiment software.

You’ll have significant influence over technical direction and full autonomy.

You’ll be working on

• Putting battle-tested learning algorithms into production.
• Building infrastructure for agent simulation, evaluation, and live code-synthesis.
• Owning the user-facing AI layer e.g. our Research Engineer agent, an AI assistant that helps the user review where their software is failing and merge in improved code/prompts/models.

What we’re looking for

• Track record of executing on projects quickly, taking full ownership of outcomes, and making trade-offs
• Substantial practical experience using LLMs in products
• Curiosity and drive to solve new problems and implement the right product form factor for a novel offering.

Why join us

• Live on the frontier of agent post-training, across multiple fronts. Prompt optimization, SFT, RL, and code synthesis. Work with a team who’s been working on the topic for years.
• Help companies across AI verticals deliver software they’re excited about and solve p0 accuracy and reliability problems for some of the best customers out there
• Operate with full ownership and autonomy

Python

• postgres, redis, modal, fastapi
• vllm, trl TS
• Next.js

Very open to changing JS if there's a good reason.