About the Role
Join a small engineering team at an AI and reinforcement learning infrastructure company. You will build quality control systems for training data and help ensure that agent evaluations produce reliable, useful results.
What You'll Do
Automate quality control for training data generated in reinforcement learning environments.
Set and enforce data quality standards using human judgment and clear evidence rather than relying heavily on large language models.
Design experiments and metrics to evaluate agent outputs.
Work with data vendors to investigate quality issues, diagnose agent failure modes, and improve data generation processes.
Turn quality findings into auditing systems, including sampling strategies and rule-based or model-assisted validation pipelines.
Improve infrastructure tools and vendor portals to reduce anomalies, inconsistencies, and edge cases.
What We're Looking For
Two to four years of experience as a research engineer or in a similar engineering or research role focused on quality control automation.
Technical education or equivalent technical experience, with proficiency in Python, Docker, and Linux.
Experience building scalable data validation pipelines and end-to-end automated QA/QC systems with autonomy in unstructured problem spaces.
Background in benchmarks and evaluations for reinforcement learning training data, including defining realistic tasks, reliable rubrics, and useful trajectories.
Experience defining and measuring training data quality, and designing evaluation metrics, experiments, and QA/QC processes.
Knowledge of statistics, strong communication skills, curiosity across domains, and the ability to collaborate independently across time zones.
Compensation & Benefits
Base salary: $100,000 to $170,000 USD annually. Visa sponsorship is available.
Location
On-site in Singapore, Singapore.