Staff ML Engineer - Enterprise AI Environments & RL

Ambral Labs; New York (NY); On-site; USD 165,000 - 325,000; Full time

Benefits offered by this job

Equity and ownership

Equinox membership

Free meals, coffee, and snacks

Health insurance

Unlimited PTO

Job summary

Ambral Labs, based in New York, is seeking an engineer to build a replayable enterprise environment engine and related evaluation systems. You’ll work with the CTO to deploy into real workflows, observe model reasoning, and grade performance against real outcomes.

The role emphasizes ownership over research direction and production systems, with opportunities to work on reinforcement learning, agent harnesses, and large-scale datasets.

Qualifications

• 1-7 years of experience building production software or machine-learning systems.
• Bonus points for reinforcement-learning environments, LLM post-training, evaluation infrastructure, agent harnesses, or closely related systems
• Understand how environment design, reward design, context, tooling, and policy behavior interact
• Turn fuzzy business objectives into tasks and signals that can be evaluated reliably
• Diagnose whether a model’s limitations come from the model itself, its context, its tools, its harness, or its training
• Move between research questions and production implementation without treating them as separate jobs
• Write strong software and can build systems that process large, messy datasets at scale
• 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

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

Skills

Production software

ML systems

Reinforcement learning

Evaluation infrastructure

Agent harnesses

LLM post-training

Job description

Ambral Labs, based in New York, is seeking an engineer to build a replayable enterprise environment engine and related evaluation systems. You’ll work with the CTO to deploy into real workflows, observe model reasoning, and grade performance against real outcomes.

The role emphasizes ownership over research direction and production systems, with opportunities to work on reinforcement learning, agent harnesses, and large-scale datasets.