Computer Vision Engineer

Company Description

Proglint Software Solutions, established in 2017, is a growing software development company specializing in custom solutions across various domains, including retail, manufacturing and artificial intelligence. Partnering with global leaders such as Fortune 500 Companies, Proglint delivers innovative solutions to tackle complex challenges. The company has also developed an in-house Computer Vision product in collaboration with international partners, addressing critical problem statements in Retail , QSR and Manufacturing. Proglint serves over 50 global customers and has created a unique platform to support small-scale businesses in digitally connecting with their clients. For more information, visit Proglint.com.

Role Description

As a Computer Vision Engineer at Proglint, you will work on developing and implementing advanced computer vision algorithms, including pattern recognition and robotics applications. Your responsibilities will include creating innovative solutions for complex problems, collaborating with a multidisciplinary team, and deploying models to real-world applications. This is a full-time, on-site role based in Chennai.

About the Role:

We are seeking a skilled and motivated Computer Vision Engineer with hands-on experience in building and deploying deep learning-based vision systems. The ideal candidate will be comfortable owning projects end-to-end from problem definition to model development and deployment and will stay updated with the latest trends in vision AI.

Key Responsibilities:

• Work with large-scale image and video datasets: cleaning, annotating, augmenting, and managing pipelines.
• Train, validate, and fine-tune deep learning models using frameworks like PyTorch or TensorFlow with hardware optimization for performance.
• Implement and optimize models for deployment on edge (Jetson, Raspberry Pi) or cloud (AWS, Azure, any other).
• Collaborate with product, hardware, and backend teams to integrate vision solutions into applications.
• Write clean, modular, and well-documented code.

Requirements:

• Bachelor's or Master's in Computer Science, AI, or a related field.
• 25+ years of hands-on experience in Computer Vision and Deep Learning.
• Strong programming skills in Python and C++.
• Hands-on experience with OpenCV, GStreamer, or DeepStream SDK.
• Solid understanding of video streaming protocols (RTSP, HLS) and frame management.
• Experience deploying CV models using TensorRT, ONNX Runtime, or similar frameworks.
• Comfort with containerization and deployment using Docker.
• Familiarity with edge computing platforms like NVIDIA Jetson, Coral, or ARM-based devices
• Design and deploy computer vision pipelines for CPU-only environments (x86, ARM, RISC-V).

Good to Have:

• Existing model optimization for better performance.
• Work with both live camera feeds (RTSP, USB) and stored media.
• Worked on large-scale video analytics projects.
• Understanding of real-time performance tuning (latency, throughput, memory management)