Software Engineer in ML

Key Responsibilities :

Model Deployment & Integration :

- Convert trained models to deployment formats (e.g., ONNX, TensorRT, OpenVINO, CoreML).

- Integrate models/algorithms provided by ML engineers into applications.

- Collaborate with Computer Vision ML engineers and testing/DevOps for production rollout.

Performance Optimization :

- Reduce latency and memory use in VA pipeline

- Optimizing and Inferencing of models

- Optimizing the code for different hardware : CPU, GPU and specialized devices, on linux and

Windows operating systems.

- Application-Level Logic & CV Algorithm Implementation

- Creating custom business logic as per clients requirement

- Implementing image processing and computer vision algorithms for diverse use cases.

Pipeline Engineering :

- Building real-time or batch inference pipelines (using frameworks like Opencv or Gstreamer).

Infrastructure & Monitoring :

- Track status of model inference time and memory..

- Monitor model performance, latency, and hardware utilization.

- Implement CI/CD for model updates.

Required Skills :

• High proficiency in C, C++
• Strong understanding of image processing, computer vision algorithms and machine learning
• High competency with image processing, computer vision and machine learning libraries such as OpenCV, Keras, OpenVino, Deepstream, Pytorch, Tensorflow
• Familiarity with Docker for containerization and deployment of applications.
• Excellent problem-solving skills and the ability to work in a fast-paced, collaborative environment.

Preferred skills :

• Familiarity with DeepStream for real-time video analytics and processing.
• Experience with OpenVINO toolkit for optimizing and deploying deep learning models on Intel hardware.
• Knowledge of ONNX Runtime for inference of models trained in popular deep learning frameworks.
• Experience with GStreamer for multimedia handling and streaming.