Your roles & responsibilities

In this role you will implement and optimize core computer vision algorithms and software. Work across model training, inference integration, and perception module deployment. Contribute to data pipeline development, system debugging, and continuous improvement cycles in an agile development environment focused on robotic autonomy.

The work model for the role is #Li_hybrid

This role is contributing to the Robotics & Discrete Automation in Bangalore India.

• Design and implement algorithms for object detection, localization, and scene understanding to support robotic manipulation and situational awareness in dynamic environments.
• Build modular vision pipelines for image acquisition, pre-processing, model inference, and post-processing. Ensure efficiency, reusability, and maintainability for real-time robotic applications. Assist in setting up training pipelines, versioning, model packaging, and deployment workflows. Use ML Ops tools to streamline model updates, performance monitoring, and continuous improvement.
• Implement and maintain well-documented APIs for perception modules and data services. Write clean, modular code and to integrate functionality across the stack. Create test suites for system validation and ensure compliance with accuracy and latency targets.
• Assist in prototyping and experimentation for new techniques and components. Contribute to rapid evaluations of feasibility, performance, and integration potential for emerging capabilities.

Qualifications for the role

• Background in Computer Science, Robotics, Machine Learning, or a related field (Bachelor’s, Master’s) with 3 to 5years of relevant experience.
• Solid foundation in computer vision and deep learning concepts, with practical experience applying them to real-world problems.
• Proficient in Python and C++ with strong software engineering fundamentals—version control, testing, debugging, and collaborative development. Exposure to system-level programming concepts such as threading, memory management, low-latency processing, and platform resource constraints.
• Exposure to machine learning frameworks (e.g., PyTorch, TensorFlow) and ML Ops tools for training, deployment, and monitoring.
• Exposure to user experience (UX) and user interface (UI) design concepts for human-centered AI applications—especially interfaces used for debugging, system control, or visualization.
• Experience on cloud technologies and data infrastructure (e.g., AWS, GCP, or Azure) for scalable training, data storage, or system integration.
• Strong problem-solving mindset, curiosity, and ability to learn quickly in a fast-paced, cross-functional environment.