Computer Vision Engineer

Lightrains Technolabs; Thiruvananthapuram; On-site; INR 1,500,000 - 2,800,000; Full time

Benefits offered by this job

5 Days Working

Flexible Timings

Access to high-end GPU compute资源

Job summary

Lightrains Technolabs is seeking a Computer Vision Engineer to build production-grade vision systems from data collection and model training to optimization and on-device deployment. You will tackle object detection, segmentation, 3D reconstruction, and multimodal AI challenges on edge and cloud targets.

We value hands-on experience with GPU-accelerated training, Python and PyTorch, OpenCV, and a strong foundation in algorithms. Collaboration with product teams is essential.

Qualifications

• 2+ years in computer vision or deep learning for detection, tracking, segmentation.
• Design, train and deploy CV models for image/video analysis pipelines.
• Collaborate with product teams to translate requirements into specs.
• Build and maintain data pipelines for large-scale datasets.
• Optimize models for inference speed and memory on edge/cloud targets.
• Stay current with vision transformers and multi-modal architectures.

Responsibilities

• Develop production-grade vision systems across data collection, training, optimization and on-device deployment.
• Implement CV pipelines for image and video analysis and ensure scalability.
• Collaborate with cross-functional teams to meet business requirements.
• Maintain and improve data pipelines for large vision datasets.

Skills

Computer vision

Deep learning

Python

C++

GPU training

Data pipelines

Edge inference

Vision transformers

Tools

PyTorch

OpenCV

scikit-image

Pillow

CUDA

Job description

We are looking for a Computer Vision Engineer who can build production-grade vision systems — from data collection and model training through optimization and on-device deployment. You will work on problems spanning object detection, semantic segmentation, 3D reconstruction, and multi-modal AI systems.

Requirements

• 2+ years of experience in computer vision and/or deep learning for object detection, tracking, and segmentation
• Design, train, and deploy CV models for image and video analysis pipelines
• Collaborate with product teams to translate business requirements into technical specifications
• Build and maintain data pipelines for large-scale vision datasets
• Optimize models for inference speed and memory efficiency across edge and cloud targets
• Stay current with advances in vision transformers, diffusion models, and multi-modal architectures

Technical Skills

• Experience training models on GPU infrastructure (NVIDIA CUDA, cloud TPUs/GPUs)
• Proficiency in Python and the vision/ML ecosystem (PyTorch, OpenCV, scikit-image, Pillow)
• Strong foundation in data structures and algorithms in Python or C++
• Hands‑on experience with data imbalance, normalization, augmentation strategies
• Experience with model evaluation, validation, and A/B testing of vision pipelines
• Familiarity with vision‑language models and generative image techniques is a plus

Perks and Benefits

• 5 Days Working
• Flexible Timings
• Access to high-end GPU compute resources