Key details
- Role type
- Full-time
- Compensation
- $400,000–$800,000/yr
- Work arrangement
- Remote
- Category
- technology
- Openings
- 1
About this role
Role Overview
Build reinforcement learning environments, training pipelines, and evaluation systems that turn frontier research ideas into scalable, high-performance AI capabilities. This remote, full-time role focuses on improving modern AI models through rigorous experimentation, synthetic data, automated quality systems, and benchmarking across complex real-world tasks.
Key Responsibilities
- Design self-contained reinforcement learning environments for complex real-world tasks, including reward functions, verifiers, and evaluation logic.
- Design and scale episode pipelines and multi-component training processes to enable reproducible experimentation.
- Build automated synthetic-data generation systems that accelerate training cycles while maintaining quality.
- Develop and integrate AI-driven evaluation and quality-assurance systems for automated grading, validation, and feedback loops.
- Fine-tune and optimize open-source reinforcement learning models using internally generated datasets and custom training strategies.
- Establish benchmarking frameworks to measure model capability, robustness, and data quality across tasks.
- Contribute to the release and analysis of evaluations on internal and external benchmark platforms.
Qualifications
- Deep experience with reinforcement learning, including environment design and training dynamics.
- A strong record of building and scaling reinforcement learning systems, pipelines, or experimentation frameworks.
- Experience with ML-oriented data design, reinforcement learning environments, reinforcement learning workflows, automation, and synthetic-data pipelines.
- Familiarity with automated evaluation systems, model validation, and quality-assurance workflows.
- Experience fine-tuning and evaluating open-source machine learning models.
- Clear technical communication and strong technical writing skills.
- Comfort working in a fast-paced, research-driven, highly collaborative environment.
Preferred Experience
- Published benchmarks, evaluations, or research artifacts.
- Familiarity with evaluation ecosystems and benchmark frameworks.
- Experience with scalable infrastructure for large-scale reinforcement learning experimentation.
Work Terms
- Full-time, remote position.
Compensation and Benefits
- The listed annual compensation range is $400,000 to $800,000.
- The stated national base-salary range is $200,000 to $300,000 USD annually.
- All employees are eligible for equity compensation and may receive performance-based bonuses, depending on role and company policy.
- Benefits include up to 100% reimbursement of health-insurance premiums, paid time off, a 401(k) plan with company matching, and additional benefits for a remote-first workforce.
Equal Opportunity
Qualified applicants will be considered without regard to race, color, religion, sex, including pregnancy, sexual orientation, or gender identity, national origin, age, disability, genetic information, veteran status, or other characteristics protected by applicable law.