About this role
The work
- Review source materials and model outputs against project guidelines, apply rubrics, and document evidence-based judgments.
- Explain your judgments clearly so feedback can improve model behavior.
- Maintain consistency and quality across repeated review tasks.
- Work with reinforcement learning environments, training pipelines, synthetic datasets, model evaluation, and benchmarking.
Requirements
- Work is remote and part-time on a contract basis.
- Professional fluency in English is required.
- Required skills include deep reinforcement learning experience covering environment design and training dynamics; experience building and scaling RL systems, pipelines, or experimentation frameworks; and proficiency with automation, data generation, and synthetic data pipelines.
- You should be familiar with automated evaluation systems, model validation, and quality assurance workflows, and experienced in fine-tuning and evaluating open-source machine learning models.
- Clear, concise communication, strong technical writing, and comfort working in fast-paced, research-driven, collaborative environments are required.
- Expert-level experience is expected.
- Experience: Expert level
- Skills: Reinforcement Learning, ML-Oriented Data Design, RL Environments, RL Workflows
Open to applicants in
- Algeria
- Argentina
- Austria
- Bahrain
- Bangladesh
- Belgium
- Brazil
- Canada
- Chile
- Colombia
- Denmark
- Egypt
- France
- Germany
- Ghana
- Greece
- India
- Indonesia
- Italy
- Japan
- Jordan
- Kazakhstan
- Kenya
- Kuwait
- Kyrgyzstan
- Lebanon
- Malaysia
- Mexico
- Morocco
- Netherlands
- Nigeria
- Oman
- Pakistan
- Palestine
- Peru
- Philippines
- Portugal
- Qatar
- Saudi Arabia
- Singapore
- South Africa
- Spain
- Sri Lanka
- Switzerland
- Taiwan
- Thailand
- Tunisia
- United Arab Emirates
- United Kingdom
- United States
- Uzbekistan
- Vietnam
Preferred
- Helpful background includes publishing benchmarks, evaluations, or research artifacts, plus experience with scalable infrastructure for large-scale RL experimentation.