mokSa.ai - Machine Learning Engineer - Computer Vision (3-6 yrs)

Job Description :

We are seeking a talented Computer Vision Engineer with strong expertise in microservice deployment architecture to join our team.

In this role, you will be responsible for developing and deploying computer vision models to analyze retail surveillance footage for use cases such as theft detection, employee efficiency monitoring, and store traffic analysis.

You will work on designing and implementing scalable, cloud-based microservices to deliver real-time and post-event analytics to improve retail operations.

Key Responsibilities :

- Develop computer vision models : Build, train, and optimize deep learning models to analyze surveillance footage for detecting theft, monitoring employee productivity, tracking store busy hours, and other relevant use cases.

- Microservice architecture : Design and deploy scalable microservice-based solutions that allow seamless integration of computer vision models into cloud or on-premise environments.

- Data processing pipelines : Develop data pipelines to process real-time and batch video data streams, ensuring efficient extraction, transformation, and loading (ETL) of video data.

- Integrate with existing systems : Collaborate with backend and frontend engineers to integrate computer vision services with existing retail systems such as POS, inventory management, and employee scheduling.

- Performance optimization : Fine-tune models for high accuracy and real-time inference on edge devices or cloud infrastructure, optimizing for latency, power consumption, and resource constraints.

- Monitor and improve : Continuously monitor model performance in production environments, identify potential issues, and implement improvements to accuracy and efficiency.

- Security and privacy : Ensure compliance with industry standards for security and data privacy, particularly regarding the handling of video footage and sensitive information.

Experience :

- 3+ years of proven experience in computer vision, including object detection, action recognition, and multi-object tracking, preferably in retail or surveillance applications.

- Hands-on experience with microservices deployment on cloud platforms (e.g, AWS, GCP, Azure) using Docker, Kubernetes, or similar technologies.

- Experience with real-time video analytics, including working with large-scale video data and camera feeds.

Technical Skills :

- Proficiency in programming languages like Python, C++, or Java.

- Expertise in deep learning frameworks (e.g, TensorFlow, PyTorch, Keras) for developing computer vision models.

- Strong understanding of microservice architecture, REST APIs, and serverless computing.

- Knowledge of database systems (SQL, NoSQL), message queues (Kafka, RabbitMQ), and container orchestration (Kubernetes).

- Familiarity with edge computing and hardware acceleration (e.g, GPUs, TPUs) for running inference on embedded systems.

Preferred Qualifications :

- Experience with deploying models to edge devices (NVIDIA Jetson, Coral, etc.)

- Understanding of retail operations and common challenges in surveillance.

- Knowledge of data privacy regulations such as GDPR or CCPA.

Soft Skills :

- Strong analytical and problem-solving skills.

- Ability to work independently and in cross-functional teams.

- Excellent communication skills to convey technical concepts to non-technical stakeholders.

Benefits :

- Competitive salary and stock options.

- Health insurance.

If you're passionate about creating cutting-edge computer vision solutions and deploying them at scale to transform retail operations, we'd love to hear from you!.

Apply Now.