Itransition

Computer Vision / ML Engineer (Industrial Inspection)

In short

This role develops a computer-vision proof of concept for detecting defects in stitched X-ray images of wind turbine blades, built with Python, OpenCV, NumPy, and pandas. The outsourcing company behind it, Itransition, serves clients like PayPal, Wargaming, and Toyota, and this specific project runs six to eight months with a possible path to a product. It demands 3+ years of CV/image-processing experience, labelling-protocol design, rigorous evaluation (recall, precision, leakage-safe splits), and large-image tiling/stitching with coordinate preservation and pytest-based testing. Remote work is restricted to candidates based in Astana/Kazakhstan.

Location: Remote, Astana
Company
Itransition delivers software projects for clients including PayPal, Wargaming, Xerox, Philips, adidas, and Toyota.
What you will do
•Develop a computer-vision proof of concept for X-ray inspection of wind turbine blades.
•Create labelling protocols, organise labelled data, cross-check annotations, and prepare exports.
•Implement, test, and document defect-detection rules with the senior engineer and NDT expert.
•Build reproducible, resumable batch-processing pipelines with versioned inputs, parameters, and outputs.
•Preserve coordinates across tiling, cropping, stitching, and report export, with automated tests.
•Build a review tool for gigapixel images, findings overlays, navigation between findings, and report export.
Requirements
•3+ years of experience in computer vision, image processing, or applied machine learning with real images.
•Strong Python skills with NumPy, OpenCV, and pandas; experience building small tools with Streamlit, Dash, Gradio, or a simple web stack.
•Experience creating or organising image labelling, including annotation protocols, consistency checks, and training-format exports.
•Knowledge of proper evaluation using recall, precision, false positives per unit, and leakage-safe dataset splits.
•Experience processing large images through tiling and reassembly while preserving coordinates, plus unit and integration testing with pytest or equivalent.
•Working English and availability for remote work from Astana/Kazakhstan.
Nice to have
•Segmentation or detection with small datasets and transfer learning.
•Radiography, medical imaging, microscopy, industrial imaging, or scientific imaging experience.
•Rule-based or hybrid pipelines combining classical detection with learned components.
•Experiment tracking, reproducible pipelines, or use of AI coding agents for prototyping and tooling.
Culture & Benefits
•Six- to eight-month proof-of-concept project with a potential path to a product.
•Flexible working hours aligned with the employee's schedule and remote-work options.
•Career development system with clear skill qualifications.
•Medical expense compensation, online English courses, and gym membership compensation.
•Five paid sick days per year without requiring a sick-leave certificate.
•Corporate events, including activities for employees' children, and corporate sports competitions.

Stop applying.
Get referred.

$10 in free credits

In just 60 seconds, fully on autopilot — Eraldt's AI agents read your CV, map the roles you fit, find live vacancies and the people who can refer you, write personal emails, and get you referred.

This isn't an application: your CV doesn't go to the company, and we don't promise a referral for this exact role.

Discover who else lands interviews on autopilot