Computer Vision Engineer 4+ Years Experience

Key Responsibilities

- Design, develop, and deploy Computer Vision and AI solutions for real-world applications.
- Develop and optimize object detection, classification, tracking, segmentation, and image/video analytics models.
- Work with YOLO (v8/v11), OpenCV, PyTorch, TensorFlow, and other deep learning frameworks.
- Develop real-time video analytics pipelines using CCTV, RTSP, IP cameras, and video streams.
- Implement multi-object tracking, counting, activity recognition, anomaly detection, and event detection.
- Perform data collection, preprocessing, annotation, augmentation, model training, validation, and optimization.
- Fine-tune pretrained models and improve accuracy, FPS, latency, and inference performance.
- Deploy computer vision models using FastAPI/Flask, REST APIs, Docker, and cloud platforms.
- Integrate AI models with databases, backend services, dashboards, and enterprise applications.
- Optimize models for GPU/CPU inference and edge deployment.
- Monitor deployed models and troubleshoot production issues.
- Collaborate with AI/ML engineers, backend/frontend developers, and business teams to deliver POCs and production solutions.

Required Technical Skills

- 4+ years of hands-on experience in Computer Vision / Deep Learning.
- Strong programming skills in Python.
- Strong experience with OpenCV, PyTorch and/or TensorFlow.




- Hands-on experience with YOLOv8/YOLOv11 or similar object detection frameworks.
- Good understanding of CNNs, object detection, segmentation, classification, tracking, and image processing.
- Experience with DeepSORT, ByteTrack, SORT, or similar tracking algorithms.
- Experience working with RTSP/IP cameras and real-time video processing.
- Knowledge of NumPy, Pandas, CUDA/GPU acceleration, and model optimization.
- Experience building and consuming REST APIs using FastAPI/Flask.
- Knowledge of Git, Linux, Docker, and basic CI/CD practices.
- Experience with AWS/Azure/GCP is an advantage.

Valuable to Have

- Experience with OCR, Face Recognition, PPE Detection, ANPR/ALPR, pose estimation, or behavioral analytics.
- Experience deploying models on NVIDIA GPUs, Jetson, or edge devices.
- Knowledge of ONNX, TensorRT, OpenVINO, or model quantization.
- Experience with MLOps and production AI deployment.
- Understanding of Generative AI/LLMs and multimodal AI is a plus.

Education

- Bachelor's/Master's degree in Computer Science, Artificial Intelligence, Data Science, Electronics, or a related field.

Candidate Profile

- Strong problem-solving and analytical skills.
- Ability to independently develop POCs and convert them into production-ready solutions.
- Good communication and teamwork skills.
- Ability to work with real-world datasets and handle model performance challenges.

📌 Computer Vision Engineer (Bhubaneswar)
🏢 Oasys Tech Solutions
📍 Bhubaneswar