Hiring CATIA Automation & AI/ML Engineer with Python

Experience: 4 To 7 Year(s)

Skill set:

CATIA Automation (Python) • Machine Learning (TensorFlow/PyTorch) • Generative Design & Surrogate Modeling • Computer Vision (OpenCV/Detectron2) • RESTful Microservices & Containerization

Domain knowledge

• Parametric 3D Modeling in CATIA: feature trees, sketch-based design, part & assembly structures
• CATIA Python/COM API Workflows: feature suppression, parameter injection, batch exports
• Generative Design & Topology Optimization: surrogate modeling, density-based and compliance-based methods
• Predictive Performance Modeling: regression and neural-network surrogates for stiffness, fatigue life, manufacturability
• Computer-Vision QA for CAD: GD&T validation, tolerance checks, feature-detection in 2D/3D views
• ROI-Driven Automation Metrics: quantifying FTE savings, accuracy improvements, cycle-time reduction

We are looking for a seasoned engineer (47 years experience) to drive our CATIA automation efforts in Python and architect AI/ML enhancements that elevate CAD-driven design and analysis. You will be the primary hands-on developer for CATIA scripting, mentor junior Python coder, and production deployment of machine-learning and AI solutions that integrate seamlessly with our CAD workflows.

Key Responsibilities

CATIA Automation (50%)

• Develop and maintain a modular Python framework (PyCATIA, pywin32) for: Parametric Part & Assembly creation, modification, and validation
• Batch exports (STEP/IGES, meshes, 2D drawings) and featurebased property injection
• Custom CLI or lightweight GUI (PyQt/Tkinter) to streamline engineer-driven workflows
• Implement robust error handling, logging, and retry logic for unattended jobs
• Integrate with Teamcenter/ENOVIA REST or ITK APIs to pull/push CAD data and metadata
• Conduct peer code reviews, establish Python style guides, and write unit- and integration-tests
  

AI/ML & Computer-Vision Integration (50%)

• Lead R&D of ML/AI models that augment CAD automation:
• Generative design (GANs, autoencoders, topology-optimization surrogates)
• Predictive performance models (regression, classification, neural nets)
• Computer-vision QA (feature detection, anomaly flagging in 2D/3D views)
• Extract CAD data (feature trees, meshes, parameters) via Python for ML pipelines
• Package inference services as Dockerized microservices with FastAPI/Flask endpoints
• Define data-collection, monitoring, and retraining strategies to ensure model performance

Mentoring

• Mentor a junior Python coder: lead pair-programming, workshops on COM automation, testing, and ML integration
• Define and enforce best practices across CAD scripts and ML artifacts:
• Git branching strategies, CI/CD for code and model builds (GitHub Actions, Jenkins)
• Documentation standards (Confluence, ReadTheDocs) and API references
• Collaborate with mechanical designers, simulation analysts, and PLM admins to gather requirements, validate outputs, and demonstrate ROI
  

Metrics, Reporting & Continuous Improvement

• Reduction in manual CAD hours per part
• Accuracy and latency of ML predictions
• Adoption rates and user satisfaction
• Build dashboards (Grafana/Prometheus) to track pipeline health, job success/failure, and resource usage