mokSa.ai - Machine Learning Engineer - Computer Vision

Job Title : Senior Machine Learning Engineer - Computer Vision AI/ML

Location : Greater Hyderabad, Telangana India

Employment Type : Full-Time

Department : Tech

mokSa.ai is specializing in AI-powered surveillance audit solutions. Founded in 2021, the company focuses on helping businesses reduce losses from shoplifting and employee fraud by leveraging computer vision and machine learning technologies

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.

Responsibilities

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

Skills & Requirements

• 7+ 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., AWS, GCP, Azure) using Docker, Kubernetes, or similar technologies.
• Experience with real-time video analytics, including working with large-scale video data and camera Skills
• Proficiency in programming languages like Python, C++, or Java.
• Expertise in deep learning frameworks (e. 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., GPUs, TPUs) for running inference on embedded
  
  

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
• 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
  
  

What We Offer

• A chance to shape the future of a high-impact AI startup
• Collaborative and innovation-driven culture
• Competitive compensation and growth opportunities
• Office located in the heart of Madhapur, Hyderabad
  
  

Ready to lead the charge?

(ref:hirist.tech)