About the job
ABOUT MITHRL
At Mithrl, we envision a future where innovative medicines are delivered to patients in mere months instead of years, and where scientific advancements occur at the speed of thought.
We are pioneering the world's first commercially available AI Co-Scientist, a transformative discovery engine that rapidly converts complex biological data into actionable insights. Scientists can pose inquiries in natural language, and Mithrl provides comprehensive analyses, novel target suggestions, hypotheses, and patent-ready documentation.
Our impressive growth reflects our success:
Achieved 12X year-over-year revenue growth
Trusted by leading biotech companies and major pharmaceutical firms across three continents
Facilitating significant breakthroughs from target discovery to patient outcomes.
ROLE OVERVIEW
We are searching for a QA Engineer specializing in Scientific Software to develop the testing, validation, and monitoring infrastructure that ensures the accuracy and reliability of the Mithrl AI Co-Scientist. This position necessitates a PhD-level scientist or computational biologist who comprehends the intricacies of the drug development lifecycle and possesses practical experience with omics data. A solid scientific foundation is crucial for assessing the biological relevance of Mithrl's outputs.
In this role, you will implement automated testing for analysis workflows, data ingestion pipelines, and discovery applications. You will establish CI systems for early regression detection, set up monitoring and alerting for system performance, and ensure every module in Mithrl generates scientifically valid and reproducible outputs. This position is a vital link between scientific knowledge and software quality engineering, essential for maintaining trust in Mithrl's analytical capabilities.
If you are a scientist passionate about product reliability, reproducibility, and the validation of machine learning-powered scientific tools, this role offers a uniquely impactful opportunity.
KEY RESPONSIBILITIES
Develop automated testing frameworks for data ingestion, analysis modules, discovery applications, and new product features.
Create scientific validation frameworks to ensure correctness and reproducibility of machine learning-driven biological analyses.
Implement continuous integration workflows that conduct end-to-end tests with every commit, identifying scientific and computational regressions.
Establish monitoring and alerting systems to track health, performance, and reliability metrics.
