Data Scientist / AI-ML Engineer

Role Overview

Advance Sensing is hiring a Data Scientist / AI-ML Engineer to develop intelligent machine learning, deep learning, computer vision, and industrial analytics solutions for advanced manufacturing applications. The engineer will work on real-world industrial datasets including machine vision images, inspection results, sensor signals, process parameters, and production data to build intelligent systems for automated defect detection, anomaly detection, predictive quality, and manufacturing process optimization. This opportunity is suitable for freshers and early-career engineers interested in building practical expertise in artificial intelligence, machine learning, deep learning, computer vision, industrial AI, and data science. The role provides exposure to complete AI development workflows including data collection, image annotation, preprocessing, model development, model training, validation, optimization, deployment, and continuous performance monitoring. As part of a multidisciplinary engineering environment working across machine vision, industrial sensing, and automation technology, the AI-ML Engineer will collaborate with application engineers, machine vision engineers, automation engineers, and software developers to transform manufacturing data into reliable industrial intelligence.

Key Responsibilities

• Develop machine learning and deep learning models for industrial inspection, quality control, and manufacturing analytics applications.
• Develop AI-based computer vision algorithms for defect detection, image classification, object detection, anomaly detection, and image segmentation.
• Work with industrial machine vision image datasets captured using area scan cameras, line scan cameras, and specialized imaging systems.
• Perform image preprocessing, augmentation, normalization, filtering, and dataset preparation for AI model development.
• Develop and train deep learning models using PyTorch, TensorFlow, or similar AI and machine learning frameworks.
• Work with OpenCV and Python-based computer vision libraries for image processing and machine vision algorithm development.
• Perform data exploration, statistical analysis, feature engineering, and visualization of industrial production datasets.
• Develop predictive analytics models for identifying process deviations, defect trends, and potential quality risks.
• Evaluate AI model performance using appropriate validation metrics and structured testing methodologies.
• Optimize trained AI models for real-time inference and deployment in industrial inspection systems.
• Support integration of AI models with machine vision software, industrial cameras, and production-line inspection applications.
• Prepare technical documentation covering datasets, training methodology, model versions, performance results, and deployment configurations.

Requirements & Tech Stack

• Good understanding of artificial intelligence, machine learning, and deep learning fundamentals.
• Strong foundation in Python programming and data handling.
• Knowledge of NumPy, Pandas, Matplotlib, Scikit-learn, or similar data science libraries.
• Basic understanding of PyTorch, TensorFlow, Keras, or similar deep learning frameworks.
• Knowledge of OpenCV and fundamental image processing concepts.
• Understanding of supervised learning, unsupervised learning, classification, regression, and clustering techniques.
• Basic knowledge of convolutional neural networks and deep learning architectures for image analysis.
• Understanding of model training, validation, testing, overfitting, regularization, and performance evaluation.
• Strong analytical thinking, mathematical reasoning, debugging, and problem-solving skills.
• Interest in industrial AI, smart manufacturing, machine vision, and automated quality inspection systems.

Preferred Knowledge

• Computer vision and industrial image processing applications.
• Convolutional Neural Networks for image classification and defect detection.
• Object detection architectures and workflows for industrial applications.
• Semantic segmentation and instance segmentation for pixel-level defect identification.
• Anomaly detection techniques for identifying previously unseen industrial defects.
• Transfer learning and fine-tuning of pretrained deep learning models.
• Dataset annotation, class balancing, and image augmentation techniques.
• Model optimization, quantization, and edge AI deployment concepts.
• Time-series analysis and predictive analytics for industrial sensor data.
• Basic understanding of SQL, databases, APIs, and data pipeline concepts.
• Understanding of MLOps concepts including model versioning, experiment tracking, and deployment monitoring.

AI and Machine Vision Applications

• Surface defect detection for scratches, dents, cracks, contamination, and manufacturing abnormalities.
• AI-based visual inspection for automated quality control systems.
• Component classification and product identification.
• Object detection and localization in industrial images.
• Image segmentation for precise defect region identification.
• Industrial anomaly detection for unknown and difficult-to-define defect categories.
• Predictive defect trend analysis using inspection and process data.
• Production quality analytics and manufacturing intelligence.
• AI-powered inspection systems for high-speed manufacturing environments.
• Edge AI inference for real-time industrial machine vision applications.

Tools and Technologies

• Python programming for AI, machine learning, and data science development.
• PyTorch, TensorFlow, or similar deep learning frameworks.
• OpenCV for image processing and computer vision development.
• NumPy, Pandas, Scikit-learn, and scientific computing libraries.
• Jupyter Notebook and modern AI development environments.
• Git and version control workflows.
• Industrial machine vision image datasets and inspection result databases.
• Edge AI and GPU-accelerated inference platforms.
• Data visualization and industrial analytics tools.

What You Will Learn

This position provides exposure beyond conventional academic AI projects. Engineers will work with real manufacturing data where factors such as illumination variation, surface texture, camera resolution, optical configuration, production speed, and defect variability directly affect AI model performance. You will gain practical experience in building complete industrial AI pipelines, from understanding an inspection problem and collecting representative data to developing, validating, and deploying models within real machine vision and industrial automation environments.

Why Join Advance Sensing?

Advance Sensing works on advanced machine vision systems, AI-driven industrial inspection, industrial sensing technology, automated quality inspection systems, and intelligent manufacturing solutions. The Data Scientist / AI-ML Engineer role provides an opportunity to work at the intersection of artificial intelligence, computer vision, industrial data analytics, and real manufacturing engineering. The position offers young engineers hands-on exposure to AI-powered machine vision systems, industrial camera datasets, deep learning-based defect detection, predictive quality analytics, and edge AI deployment. By working alongside teams involved in machine vision, sensing technology, industrial automation, and smart manufacturing, the engineer will gain an understanding of how AI algorithms move from research and experimentation into reliable production systems.

Who Should Apply?

This role is suitable for candidates who enjoy solving technical problems using data, algorithms, and experimentation. Candidates should be curious about how artificial intelligence can solve real industrial problems and should be willing to work with complex datasets, challenging visual inspection problems, and practical deployment constraints. Fresh graduates and candidates with up to two years of experience in data science, machine learning, deep learning, computer vision, image processing, or related software development areas are encouraged to apply.