About the Role

We’re looking for an end-to-end Computer Vision Engineer to build, deploy, and monitor real-time video analytics systems on edge and Linux environments. You’ll work across model development (detection, segmentation, classification, tracking), real-time inference optimization, and API integration for production-grade deployments.

Key Responsibilities

- Build production computer vision systems end to end: requirements, data preparation, model development, deployment, and monitoring
- Develop and fine-tune models for object detection, segmentation, classification, and tracking
- Manage data quality and evaluate models using mAP, IoU, Dice, precision/recall, and F1
- Deploy real-time video pipelines using OpenCV, GStreamer, and FFmpeg
- Optimize inference with ONNX, TensorRT, and OpenVINO for real-time and edge scenarios
- Build APIs with FastAPI or Flask and deploy services on Linux, using Docker where applicable
- Collaborate with backend teams, communicate technical trade-offs, and integrate CV components into larger systems
- Contribute to monitoring and logging of deployed CV/ML systems (e.g., MLflow, Weights & Biases)

Required Qualifications

- About 3+ years of hands-on computer vision / ML engineering experience.




- Robust Python programming skills
- Strong FastAPI skills for API development
- Strong experience with PyTorch
- Experience with at least one of: detection, segmentation, tracking, or classification models
- Practical understanding of mAP, IoU, Dice, precision/recall, and F1
- Experience deploying on Linux environments
- Ability to debug models and pipelines using metrics and logs
- Strong problem-solving and communication skills
- Comfortable in a research-driven environment, with a hands-on builder mindset

Preferred Qualifications

- GStreamer, FFmpeg, and RTSP streaming
- ONNX, TensorRT, and OpenVINO for model optimization
- Edge deployment (NVIDIA Jetson, ARM, embedded Linux)
- Familiarity with YOLO, Detectron2, ViT/Swin, SAM, and CLIP
- Docker and CI/CD
- Annotation tools such as CVAT and Label Studio
- MLflow or Weights & Biases; monitoring/logging for ML/CV pipelines
- Exposure to LLMs and speech AI

How to Apply

Apply via Indeed with your updated resume. Please include links to relevant projects, GitHub, or deployed CV work if available.

Pay: ₹1,000,000.00 - ₹1,500,000.00 per year

Work Location: In person

📌 Computer Vision Engineer (Bengaluru)
🏢 McLaren Strategic Solutions
📍 Bengaluru