19 hours ago
Singapore, SingaporeMid Level / Senior
Base Salary
$100k - $170k/yr
Responsibilities
- Automate quality control for training data produced within reinforcement-learning environments.
- Define and enforce training-data quality standards using human judgment and domain understanding.
- Design experiments and metrics to evaluate agent outputs.
- Investigate quality issues with data vendors, identify agent failure modes, and improve data-generation processes.
- Build auditing systems with sampling strategies and rule-based or model-assisted validation pipelines.
- Integrate quality improvements into platform infrastructure and vendor tools to reduce anomalies and inconsistencies.
Requirements
- Two to four years of experience in research engineering or a 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 reinforcement-learning data benchmarks and evaluations, including task design, rubrics, and 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, curiosity, independence, and comfort working in a fast-paced startup environment across time zones.
Benefits
- Salary of $100,000 to $170,000 USD annually.
- Visa sponsorship is available.
- On-site work in Singapore, Singapore.