About the Role
Join an early-stage AI infrastructure team focused on reinforcement learning environments and model evaluation. In this role, you will build quality control systems for training data, helping scale reliable data creation and improve agent performance evaluation.
What You'll Do
Automate quality control for training data created within reinforcement learning environments.
Define and enforce data quality standards using human judgment and domain understanding.
Design experiments and metrics to assess agent outputs.
Work with data vendors to investigate quality issues, identify 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.
Integrate quality improvements into platform infrastructure and vendor tools to reduce anomalies and inconsistencies.
What We're Looking For
Two to four years of experience in a research engineering or similar role focused on quality control automation.
A degree in a technical field and proficiency with Python, Docker, and Linux.
Experience building scalable data validation pipelines and automated QA/QC systems end to end, including in unstructured problem spaces.
Background in benchmarks and evaluations for reinforcement learning data, including realistic task design, reliable rubrics, and useful training trajectories.
Experience defining training data quality standards and building systems guided by human judgment rather than heavy reliance on language models.
Knowledge of statistics and experience designing metrics, experiments, and quality assurance processes.
Clear communication skills, curiosity, independence, and comfort working in a fast-paced startup environment across time zones.
Compensation & Benefits
Salary: $100,000 to $170,000 USD annually. Visa sponsorship is available.
Location
On-site in Singapore, Singapore.