Computer Vision Engineer

What You'll Do

Develop and deploy computer vision systems for

object detection, segmentation, tracking, pose estimation, and scene understanding

Train and optimize deep learning models using YOLO, CNNs, Transformers, and related architectures

Build robust vision pipelines using Python, OpenCV, PyTorch/TensorFlow, and GStreamer

Deploy and optimize models for real-time inference on edge and embedded devices

Work with image/video datasets including data collection, annotation, preprocessing, and curation

Debug and improve vision pipelines in real-world industrial environments

Integrate Vision AI systems with embedded hardware, robotics, and autonomous equipment

Collaborate closely with robotics, firmware, and hardware engineers

Test, validate, and continuously improve models based on field performance and edge cases

Document models, datasets, experiments, and system performance

What We're Looking ForStrong Fundamentals

Solid understanding of

computer vision and image processing

Strong Python programming skills

Good understanding of deep learning and neural networks

Experience with object detection and segmentation

Hands-on experience with PyTorch, TensorFlow, or similar frameworks

Strong understanding of OpenCV and image/video processing

Experience working with GStreamer pipelines

Hands-on Experience

Building and training computer vision models

Preparing and working with image/video datasets

Deploying and optimizing models for production

Testing and validating vision systems

Debugging complex vision pipelines

Working with real-world, noisy, and unstructured data

Good to Have

Experience with

NVIDIA Jetson or other edge AI platforms

Model optimization, quantization, or TensorRT

Experience with ROS / robotics

Exposure to 3D vision, depth estimation, or SLAM

Experience with autonomous systems or industrial automation

Experience integrating AI models with embedded hardware

Computer Science, Electronics, Robotics, or related educational background

Personal/academic computer vision projects, publications, or open-source contributions

What You'll Get

Work on

real-world robotics, industrial automation, and autonomous systems

Own projects across the complete computer vision/ML pipeline

Deploy AI models on actual production hardware

Hands-on exposure to edge AI, embedded systems, robotics, and industrial environments

Work closely with experienced AI/ML, robotics, firmware, and hardware engineers

High ownership and the opportunity to make a visible impact

Fast-paced startup environment with significant learning and growth opportunities

Opportunity to grow into AI/ML engineering, robotics, or technical leadership roles

Who Should Apply?

We’d love to hear from you if you:

Are genuinely passionate about

Computer Vision and AI

Enjoy building things and solving problems hands-on

Like debugging complex vision systems and improving model performance

Want to bridge AI/ML with physical systems and hardware

Have built meaningful computer vision projects through work, internships, college, or independently

Are excited about robotics, autonomous systems, or industrial automation

About Control One

Control One

is a Bengaluru-based AI startup building intelligent systems for industrial automation.

We work at the intersection of

robotics, computer vision, and real-world factory and warehouse environments

, developing Vision AI products that make industrial equipment smarter, safer, and more productive.

From forklifts and material handling equipment to press and stamping lines, we build technology for the machines and people operating them every day.