Data Preprocessing Model Specialist (MednTech)
Actively Interviewing
This organisation is scheduling interviews as applications come in. They're ready to hire as soon as they find the right person. Don't miss your opportunity, apply now!
MednTech
We provide an Android AI tool that analyzes cervical images to support frontline screening decisions.
Data Preprocessing Model Specialist-Input Quality & Standardization
About MednTech
MednTech is a nonprofit organization developing AI-powered tools to improve early detection of cervical cancer and expand access to care in underserved communities, particularly in Africa. It works by equipping frontline healthcare providers with accessible technology and partnering with local health systems to improve outcomes and empower patients. We have already implemented our diagnostic model in real-world settings in Rwanda. We are now looking to further improve its performance and robustness before our next deployment, and are currently seeking volunteers to support this initiative.
Why Volunteer With Us
We are early-stage, moving fast, and building something that matters. You will have real ownership over technical decisions that directly shape a tool going into the field. Cervical cancer is one of the most preventable cancers in the world, yet it remains a leading cause of cancer death in low-resource settings simply because screening does not reach the people who need it. The tool you help build changes that. If you want your code to save lives, this is that opportunity!
Role Overview
Your role will be to aid design and implement a preprocessing model that ensures all incoming cervical images meet strict quality and consistency standards before being passed into downstream models.
Our cervical cancer screening method is dependent on pictures taken using a smartphone, leading to large variation in lighting and cervix positions in the image. On top of natural variances in fluid blockages or rotation and angle or cervix, it’s important that only valid images are run through our model.
Key Responsibilities
- Build automated checks for:
- Lighting normalization
- Blur and focus detection
- Angle and framing validation
- Specular reflection handling
- Develop preprocessing models or heuristics to:
- Enhance image quality (contrast, de-noising)
- Standardize image format, resolution, and scale
- Implement image rejection and acceptance criteria pipeline
- Create a quality scoring system for input images
- Collaborate with CV and ML engineers to optimize preprocessing impact on performance
- Optimize preprocessing for real-world noisy data (mobile capture, low-resource settings)
Required Skills
- Strong background in computer vision fundamentals
- Experience with OpenCV, PIL, or similar image processing libraries
- Understanding of image quality metrics
- Experience building automated data validation pipelines
Preferred Qualifications
-
Experience with medical image preprocessing
-
Familiarity with variability across capture devices and environments
-
All roles are highly collaborative and will work closely across the MednTech AI pipeline
-
Experience with healthcare AI, low-resource environments, or global health applications is a strong plus
-
Candidates should be comfortable working in fast-paced, early-stage environments
Minimum Hours per Week:
4-6 hours per week
Duration:
One-off project
Non Charity Employer
6 - 10
We connect professionals with impact startups matching their causes, skills & schedule.
The client requests no contact from agencies or media sales.
