Staff ML Engineer: RL Environments & Production Systems

Ambral; New York (NY); On-site; USD 120,000 - 180,000; 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 Labs is hiring to grow its founding team in New York. You will work at the center of a replayable environment engine that reconstructs enterprise worlds from the past and exposes state through production-grade tools used by agents.

You’ll collaborate across research, infrastructure, and production systems with direct interaction with the CTO to test research against real business problems. The role emphasizes turning complex objectives into measurable signals, building scalable systems

Qualifications

• 1-7 years of experience building production software or machine-learning systems.
• Bonus points for reinforcement-learning environments, LLM post-training, or evaluation infrastructure.
• You understand how environment design, reward design, context, tooling, and policy behavior interact.
• You can turn fuzzy business objectives into tasks and signals that can be evaluated reliably.
• You can diagnose whether a model’s limitations come from the model itself, its context, its tools, its harness, or its training.
• You can move between research questions and production implementation without treating them as separate jobs.
• You write strong software and can build systems that process large, messy datasets at scale.
• You care about reproducibility, observability, and understanding why a model behaves the way it does.
• You’re looking to do the best work of your life and build something you’ll be proud of for decades

Responsibilities

• Designing and implementing a replayable environment engine for enterprise workflows.
• Building an environment factory that converts historical data and task definitions into runnable environments.
• Designing graders that translate business objectives into verifiable rewards.
• Developing methods to mine useful tasks, trajectories, and evaluation cases from historical workflows.
• Creating eval sets that are representative, reproducible, and resistant to overfitting.
• Finding optimal model/tool/context/policy combinations to maximize performance while reducing cost.
• Training and evaluating agents operating over long horizons and large tool spaces.
• Building replay and observability systems to make agent behavior explainable and measurable.
• Scaling from individual environments to thousands of concurrent runs.
• Owning the research direction and production systems end-to-end.

Skills

Production software

Machine learning systems

Research to production

Reinforcement learning

Problem solving

Tools

Python

TensorFlow/PyTorch

Git

Linux

Job description

Ambral Labs is hiring to grow its founding team in New York. You will work at the center of a replayable environment engine that reconstructs enterprise worlds from the past and exposes state through production-grade tools used by agents.

You’ll collaborate across research, infrastructure, and production systems with direct interaction with the CTO to test research against real business problems. The role emphasizes turning complex objectives into measurable signals, building scalable systems