N
nanvia muse
AI Computer Vision Engineer
TN, INPosted 2d ago
Computer VisionMid LevelFull-time
About the Role
**Job Responsibilities** **and Accountabilities**
* Design, train and evaluate models for detection, classification, segmentation, recognition and multi\-object tracking.
* Develop video analytics for re\-identification, activity recognition, behavioural analysis and event detection.
* Build low\-latency inference pipelines for live and recorded video streams, including RTSP and camera feeds.
* Optimize and deploy models using ONNX, TensorRT, Triton, DeepStream and NVIDIA Jetson platforms.
* Integrate AI outputs with backend services, APIs, VMS and edge devices.
* Measure and improve accuracy, false alarms, tracking stability, latency, throughput, FPS and resource usage.
* Support dataset preparation, annotation, augmentation, validation and difficult\-edge\-case analysis.
* Document model architecture, test results, deployment configuration, limitations and operational guidance.
**Experience Required**
* 3–5 years of professional computer vision, machine learning or video analytics experience.
* Hands\-on experience with at least two areas: detection, tracking, re\-identification, segmentation, recognition or behaviour analysis.
* Experience deploying and optimizing models outside research notebooks on GPU or edge hardware.
* Experience integrating vision models into real\-time or backend software systems.
**Qualifications**
* Bachelor’s degree in Computer Science, AI, Machine Learning, Computer Engineering, Electronics Engineering or a related field.
* Equivalent practical experience supported by a strong project portfolio may be considered.
**Technical Skills Required**
* Strong Python and working knowledge of C\+\+ for performance\-sensitive integration.
* PyTorch or TensorFlow, OpenCV, Linux, Git, testing and Docker.
* Object detection, tracking, image/video processing and quantitative model evaluation.
* ONNX, TensorRT and real\-time inference optimization; quantization, pruning or mixed precision is preferred.
* NVIDIA Jetson, DeepStream, GStreamer, Triton or Metropolis experience is strongly preferred.
* RTSP/video\-stream pipelines, backend integration, performance profiling and production monitoring.
**Soft Skills**
* Strong analytical troubleshooting and systematic edge\-case investigation.
* Ability to balance model quality with latency, throughput and hardware constraints.
* Clear communication, documentation, ownership and multidisciplinary collaboration.
Pay: ₹1,500,000\.00 \- ₹3,000,000\.00 per year
Benefits:
* Health insurance
* Provident Fund
Work Location: In person
* Design, train and evaluate models for detection, classification, segmentation, recognition and multi\-object tracking.
* Develop video analytics for re\-identification, activity recognition, behavioural analysis and event detection.
* Build low\-latency inference pipelines for live and recorded video streams, including RTSP and camera feeds.
* Optimize and deploy models using ONNX, TensorRT, Triton, DeepStream and NVIDIA Jetson platforms.
* Integrate AI outputs with backend services, APIs, VMS and edge devices.
* Measure and improve accuracy, false alarms, tracking stability, latency, throughput, FPS and resource usage.
* Support dataset preparation, annotation, augmentation, validation and difficult\-edge\-case analysis.
* Document model architecture, test results, deployment configuration, limitations and operational guidance.
**Experience Required**
* 3–5 years of professional computer vision, machine learning or video analytics experience.
* Hands\-on experience with at least two areas: detection, tracking, re\-identification, segmentation, recognition or behaviour analysis.
* Experience deploying and optimizing models outside research notebooks on GPU or edge hardware.
* Experience integrating vision models into real\-time or backend software systems.
**Qualifications**
* Bachelor’s degree in Computer Science, AI, Machine Learning, Computer Engineering, Electronics Engineering or a related field.
* Equivalent practical experience supported by a strong project portfolio may be considered.
**Technical Skills Required**
* Strong Python and working knowledge of C\+\+ for performance\-sensitive integration.
* PyTorch or TensorFlow, OpenCV, Linux, Git, testing and Docker.
* Object detection, tracking, image/video processing and quantitative model evaluation.
* ONNX, TensorRT and real\-time inference optimization; quantization, pruning or mixed precision is preferred.
* NVIDIA Jetson, DeepStream, GStreamer, Triton or Metropolis experience is strongly preferred.
* RTSP/video\-stream pipelines, backend integration, performance profiling and production monitoring.
**Soft Skills**
* Strong analytical troubleshooting and systematic edge\-case investigation.
* Ability to balance model quality with latency, throughput and hardware constraints.
* Clear communication, documentation, ownership and multidisciplinary collaboration.
Pay: ₹1,500,000\.00 \- ₹3,000,000\.00 per year
Benefits:
* Health insurance
* Provident Fund
Work Location: In person
Similar Jobs
L
Lunaroutpost• 3mo ago
Senior Software Engineer - Perception
Golden, ColoradoFull-time
A
ASOS.com• 1mo ago
Senior AI Engineer – Machine Learning (Computer Vision)
London, England, UKFull-time
E
Ecopiatech• 7mo ago
Software Engineer - Computer Vision
Toronto, OntarioFull-time
U
University of Derby• 1mo ago
AI, Computer Vision & Digital Twin Engineer (KTP Associate)
Derby, England, UKFull-time