About the job
About Pangram Labs
At Pangram Labs, we are committed to safeguarding authenticity by developing the most advanced AI detection systems in the world. Our team is at the forefront of research, publishing innovative techniques and algorithms, while also creating products that seamlessly integrate our technology into everyday life.
We are actively seeking highly motivated, mission-oriented individuals who possess a passion for building impactful solutions to join our dynamic team. All positions are based in our Brooklyn, New York office.
About the Role
We are in search of an AI Tooling and Evaluation Engineer to become a vital part of our AI research team. In this role, you will collaborate closely with AI research scientists and engineers to design and develop internal tools, platforms, and systems that support the entire model development lifecycle—from data collection and annotation to evaluation and deployment monitoring.
This full-stack software engineering position focuses on providing research support. You will primarily focus on constructing web applications, APIs, and data pipelines, alongside having a foundational understanding of machine learning concepts to effectively grasp the needs of the research team.
Roles and Responsibilities:
- Develop evaluation infrastructure for standardized model assessments and monitoring, including dashboards and reporting tools to track performance over time.
- Oversee Label Studio deployment for data annotation initiatives.
- Design browser-based interfaces for exploratory data analysis on training datasets.
- Create research support systems to monitor user engagement with the platform.
- Enhance and maintain synthetic data generation workflows.

