ml engineer for industrial inspection

Itransition delivers projects for clients including PayPal, Wargaming, Xerox, Philips, Adidas, and Toyota.

• Write the labelling protocol with the senior engineer and the NDT expert; label, cross-check, fix, and export data;
• Implement, test, and document defect rules designed with the senior engineer and the NDT expert;
• Implement the agreed detection rule for the specific detectable bondline condition if the feasibility gate passes;
• Build reproducible batch pipelines with versioned inputs, parameters, and outputs that can be resumed on large images;
• Preserve coordinates across tiling, cropping, stitching, and report export, with automated tests;
• Calibrate thresholds on reference samples with known defects;
• Compute and report metrics per physical defect and per metre of blade before and after tuning;
• Build the review tool with gigapixel images, overlaid traces and findings, finding navigation, and report export;
• Prepare the tooling and data package for independent annotation of the control image by the NDT expert;
• Keep control-image labels sealed until the pipeline and thresholds are frozen, then import them and run the evaluation;
• Investigate every miss and the main false positives with the senior engineer.

• 3+ Years of experience in computer vision, image processing, or applied ML with real images;
• Python with NumPy, OpenCV, and pandas;
• Experience building small tools with Streamlit, Dash, Gradio, or a simple web stack;
• Experience labelling or organising labelling, including protocols, annotator consistency checks, and training-format exports;
• Knowledge of proper evaluation with recall, precision, false positives per unit, and leakage-free splits between crops of the same physical object;
• Experience with large images, including tiling, reassembly, and coordinate preservation across tiles, crops, and full images;
• Experience with unit and integration tests using pytest or an equivalent tool;
• Experience with reproducible runs using versioned inputs, parameters, and outputs;
• A project where you learned an unfamiliar domain quickly and can explain what you read and whom you asked;
• Working English;
• Nice to have: Segmentation or detection with small datasets, transfer learning, radiography, medical imaging, microscopy, industrial or scientific imaging, rule-based and hybrid pipelines, experiment tracking, reproducible pipelines, AI coding agents for prototyping and tooling.

• Competitive compensation depending on qualification and skills;
• Career development system with clear skill qualifications;
• Flexible working hours aligned to the employee’s schedule;
• Corporate medical insurance covering private and public medical centers;
• Online English courses;
• Corporate parties and events for employees and their children;
• Internal conferences, workshops, and meetups for learning and experience sharing;
• Gym membership compensation;
• 5 Days of paid sick leave per year without requiring a sick-leave certificate;
• The project is planned for six to eight months with a path to a product.