VISION SYSTEMS ARCHITECT

Industrial vision systems that remove uncertainty from production

I architect camera-to-decision systems for factories and robotics teams that cannot afford fragile demos: Vision hardware selection and design, Multi-camera acquisition, edge AI, traceability, storage, commissioning, and support built into one reliable workflow from a practical vision systems designer.

Lead Vision Engineer
Northvolt
ABB Robotics R&D
MSc Robotics and Control
Vision Systems Architect

View systems Open LinkedIn

SELECTED VISION SYSTEMS

Selected systems engineered for real operating conditions

Each case study is framed around the decisions that matter when a vision system has to leave the demo table: acquisition, perception, control, traceability, support, and deployment risk.

Gnutti production vision system visual: PLC Event, Camera Group, FrameSet, AI / Rules, Traceability + Result.

Gnutti Carlo GroupJuly 2025 - Present

Industrial Vision System Design

Lead Vision Systems Engineer

Built the architecture and leading the team for a PLC-driven production vision system: retrofitting vision hardware in the existing production line, synchronized camera triggering, image acquisition, AI decision flow, traceability storage, commissioning checks, and support-ready diagnostics, designed methods for measurement system analysis (MSA).

PLC handshakeGigE VisionMulti-camera acquisitionAI inspectionTraceabilityCommissioningMeasurement System Analysis (MSA)

View case study

Northvolt production machine-vision visual: industrial cameras, line-scan imagery, calibration checks, analysis flow, vendor inspection review, and production debugging signals.

NorthvoltFeb 2024 - Jun 2025

Production Machine Vision Engineering

Machine Vision Engineer

Delivered production machine-vision work across line-scan and area-scan imaging, calibration, lighting validation, OpenCV-based analysis, C++/Python debugging, and industrial vendor platforms under real manufacturing constraints.

Line-scan imagingArea-scan imagingCalibrationOpenCVC++ / PythonVendor vision platforms

View case study

ABB robotic perception mining visual: mobile robot camera scan, point-cloud obstacle detection, 3D localization overlays, ROS 2-style signal flow, and simulation review frame.

ABB Robotics R&DApr 2023 - Oct 2023

Robotic Perception for Mining Automation

Robotics R&D Engineer

Built a robotic perception workflow for mining automation using ROS 2, YOLO object detection, point-cloud position estimation, and Gazebo simulation to translate visual detections into spatial information usable by robotic system logic.

ROS 2YOLO detectionPoint-cloud localizationGazebo simulationRobotic perceptionPython

View case study

National Centre of Robotics & AutomationSep 2020 - Jun 2021

Vision-Based Human-Following Robot

Research Intern

Built a vision-based human-following robotics workflow using visual tracking, KD-tree target association, Kalman filtering, ROS 1, motor control, Gazebo simulation, and Dijkstra path planning.

Visual trackingKD-tree associationKalman filteringROS 1Motor controlDijkstra planning

View case study

EXPERIENCE MAP

From research prototypes to production systems that survive factory reality

I bring the rare combination hiring teams look for but often struggle to find: robotics research depth, industrial machine-vision delivery, PLC-aware production thinking, and the discipline to make a system supportable after launch.

Explore capabilities Email Umair

VISION STACK

One accountable system from PLC event to operator decision

My work sits where teams usually lose time: between cameras, automation, IT/OT, quality, mechanical constraints, maintenance, storage, databases, and deployment. I connect those pieces so the result is not just detection, but a decision process people can trust.

Explore capabilities Email Umair

CAPABILITIES

One engineering owner across cameras, PLCs, edge AI, and traceability

End-to-end solution design

I do not stop at a proof of concept. I design the path from first image to commissioned station, support model, release practice, and repeatable rollout.

Industrial machine vision

Multi-camera acquisition, line-scan and area-scan systems, OpenCV, calibration, lighting, image quality, and AI inference handled as production engineering, not decoration.

Vision systems architecture

PLC handshakes, edge reliability, NAS/image storage, database traceability, diagnostics, and reporting designed so problems are visible, recoverable, and explainable.

Profile signal

Lead Vision Engineer at Gnutti Carlo Group SwedenMachine Vision Engineer at NorthvoltRobotics R&D Engineer at ABBMSc Computer Science, Robotics and Control, Umea UniversityBSc Mechatronics Engineering, NUST

Recognition

3rd Prize - International Competition of Autonomous Running Robots 2020
Winner of Tennis in EME Olympiad 2019

CONTACT

Bring me in when vision reliability matters.

If your team needs industrial vision, robotics perception, automation, edge AI, traceability, or production deployment, I can help turn uncertainty into a system that is specified, built, validated, and trusted.

Email Umair Open LinkedIn