Member of Technical Staff (Evals & Post-Training)

At the center of Ambral Labs is a replayable environment engine for the enterpirse.

The system reconstructs a company’s world as it existed at a particular moment in the past then exposes that state through the same tools an agent would use in production. This lets us place new policies and agent configurations inside real historical environments, observe how they reason and act, and grade their performance against real outcomes.

You'll work across research, infrastructure, and production systems including:

-

Building an environment factory that converts recorded enterprise data and task definitions into runnable environments

-

Designing graders that turn ambiguous business objectives into verifiable rewards

-

Developing methods for mining useful tasks, trajectories, and evaluation cases from historical workflows

-

Creating eval sets that are representative, reproducible, and resistant to overfitting