Founding Research Engineer - Enterprise RL & Environments

Ambral (YC S25); New York (NY); On-site; USD 215,000 - 330,000; Full time

Benefits offered by this job

Significant equity and ownership

Equinox membership

Free meals, coffee, and snacks

Health insurance

Unlimited PTO

Job summary

Ambral is building a replayable environment engine over real enterprise history to improve model performance while reducing inference cost. You will own the research and infrastructure to turn this into a scalable model-improvement system.

Core tasks include building an environment factory, designing graders, mining tasks, creating eval sets, and optimizing model-tools-context-policy combinations. You will work directly with the CTO, deploying into real enterprise workflows and testing research

Qualifications

• 4+ years of experience building production software or ML systems.
• Experience with reinforcement-learning environments, post-training, or evaluation infra.
• Ability to turn fuzzy business objectives into measurable tasks and signals.

Responsibilities

• Build an environment factory converting recorded data into runnable environments.
• Design graders to turn business objectives into verifiable rewards.
• Mine useful tasks, trajectories, and evaluation cases from historical workflows.
• Create eval sets that are representative, reproducible and resistant to overfitting.
• Find combinations of models, tools, context and policies to maximize performance while reducing inference cost.
• Train and evaluate agents that operate over long horizons and large tool spaces.
• Build replay and observability systems for explainable, measurable behavior.
• Scale from individual environments to thousands of concurrent runs.

Skills

Reinforcement learning

LLM evaluation

Production software

Observability

Scalability

Tools

Python

PyTorch

TensorFlow

ML tooling

Job description

Ambral is building a replayable environment engine over real enterprise history to improve model performance while reducing inference cost. You will own the research and infrastructure to turn this into a scalable model-improvement system.

Core tasks include building an environment factory, designing graders, mining tasks, creating eval sets, and optimizing model-tools-context-policy combinations. You will work directly with the CTO, deploying into real enterprise workflows and testing research