Image Processing Engineer

Image Processing Engineer

Pittsburgh, PA

Full-time

Blade Diagnostics is the world leader in turbo-machinery mistuning inspection and analysis and our proprietary technologies make advanced turbo-machinery safer and less expensive to operate. Blade Diagnostics customers include jet-engine manufactures, power generation equipment providers and the US Department of Defense (DOD).

Originally spun out of Carnegie Mellon University in 2004, Blade Diagnostics is based in Pittsburgh, Pennsylvania. Our technology protects and repairs jet engine bladed disks for the DOD and jet engine manufacturers.

Teamwork and mutual respect are core aspects of our culture. This culture of support and respect results in an exciting and dynamic workplace. Blade Diagnostics is looking for a special individual to contribute to designing, manufacturing, testing, and installation and service of new and existing products for our customers. Responsibilities of the position include hands-on designing, building, integrating, testing and maintaining various elements of our world-class products as a member of the Blade Diagnostics team.

Key RESPONSIBILITIES INCLUDE:

· Algorithm & Model Development: Design and train deep learning models for anomaly detection specifically tuned for industrial surface inspection.

· Data Pipeline Engineering: Develop code to process, clean, and annotate large datasets of metal part imagery. Implement robust data augmentation strategies to account for varying lighting, angles, and surface reflections.

· Production-Ready Coding: Write clean, efficient, and scalable code (primarily in MATLAB, Python and C++) to deploy inference models into production environments or edge devices.

· System Integration: Collaborate with hardware and automation teams to integrate camera systems, lighting setups, and software pipelines, ensuring optimal image capture for highly reflective metal surfaces.

· Performance Evaluation: Establish rigorous testing protocols to evaluate model accuracy, precision, recall, and false-positive rates. Continuously iterate on models to minimize escaped defects.

Required Qualifications & Skills

· Degree in Computer Science, Electrical Engineering, Machine Learning, or a related field (Graduate Degree preferred).

· 3+ years of professional, hands-on experience in computer vision, image processing, and machine learning.

· Programming Languages: Expert-level proficiency in MATLAB, Python and strong experience with C++ for performance-critical deployments.

· Computer Vision Libraries: Extensive experience with OpenCV, scikit-image, and similar traditional image processing libraries.

· Data Handling: Experience working with large-scale image datasets, including automated labeling pipelines, data version control (e.g., DVC), and handling class imbalances (which are common in defect detection).

PREFERRED SKILLS AND QUALIFICATIONS:

· Industrial/Manufacturing Experience: Previous work in automated optical inspection (AOI), non-destructive testing (NDT), or quality control environments.

· Metallurgy/Optics Knowledge: Understanding the challenges of imaging metal (e.g., handling specularity, glare, anisotropic textures) and experience specifying industrial lighting (e.g., polarized, diffuse, or structured light).

· Edge Deployment: Experience deploying models on edge hardware, or working with NVIDIA Jetson devices.

· MLOps: Familiarity with deploying and monitoring ML models in production.

Candidate Profile

· Problem Solver: You enjoy tackling complex, messy real-world data rather than just perfectly curated benchmark datasets.

· Detail-Oriented: You understand that in quality control, a single missed defect (false negative) can have significant downstream consequences.

· Collaborative: You communicate complex AI concepts clearly to non-technical stakeholders and hardware engineers.

· Strong interpersonal skills and support of BDC corporate culture

· Compliance with US Government Export Control/ITAR/Cyber Security requirements

· Ability to obtain access to US military base/facility

· Familiarity with running MATLAB code/scripts

· Ability to work in both office and industrial environments

· Ability to handle a fast-paced, evolving engineering and development environment

To conform to U.S. Government technology export regulations, including the International Traffic in Arms Regulations (ITAR) any potential candidate must be a U.S. citizen, lawful permanent resident of the U.S., protected individual as defined by 8 U.S.C. 1324b(a)(3), or eligible to obtain the required authorizations from the U.S. Department of State.

Blade Diagnostics Corporation does not discriminate on the basis of race, color, religion, sex (including pregnancy and/or gender identity), national origin, political affiliation, sexual orientation, marital status, disability, genetic information, age, membership in an employee organization, retaliation, parental status, military service, or other non-merit factor, and provides reasonable accommodations in compliance with the Americans with Disabilities Act (42 U.S.C. 12101).