Staff AI Engineer - RL Environments & Agent Training

United States Digital Space LLC; United States; Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Lunch stipend

Health and dental benefits

RRSP matching / 401K

Parental Leave top-up

Enrichment benefits

Learning stipend

6 weeks paid vacation

Travel to other offices

Home office stipend

Job summary

the company, a global security-first enterprise AI company, seeks an engineer to build RL environments and evaluate agents in real-world enterprise tasks. You will design diverse environments, run agents, and iterate on both agents and environments to improve performance.

You will collaborate with modeling and product teams, work with external vendors to craft high-quality RL environments, and automate discovery of capability gaps while tracking measurable improvements across evals and training.

Qualifications

• You have engineered agents and optimized them for specific industry use cases.
• You have spent dozens of hours reviewing agent trajectories and fixing issues with training or harness engineering.
• You obsess over measuring agentic capabilities and turning that into repeatable processes.

Responsibilities

• Build new RL environments targeting different agentic capabilities and industry areas
• Train and evaluate agents in those environments
• Make all pieces work together: tasks, data, tool implementations, and verifiers
• Work across modeling and product to identify gaps in agent performance, and improve both the agents and the environments
• Collaborate with external vendors to create high-quality RL environments and tooling to ensure high quality tasks, data, and verifiers
• Automate discovery of model capability gaps and measure agent performance during evals and training

Skills

Agent development

RL environments

Model training

Verifier implementations

Annotation workflows

Synthetic data pipelines

Hands-on debugging

Tools

None

Job description

the company, a global security-first enterprise AI company, seeks an engineer to build RL environments and evaluate agents in real-world enterprise tasks. You will design diverse environments, run agents, and iterate on both agents and environments to improve performance.

You will collaborate with modeling and product teams, work with external vendors to craft high-quality RL environments, and automate discovery of capability gaps while tracking measurable improvements across evals and training.