Robotics Software Intern

Location: Bangalore

Type: Full-time

About the Role

We are seeking a passionate Robotics Software Intern to focus on intelligent perception and learning pipelines for autonomous robots. This is not about running pre-written code—it’s about building, training, and refining algorithms that can perceive, understand, and act in complex environments. You’ll work alongside our core software engineers, complementing their work by bringing depth in reinforcement learning, computer vision, and AI-driven perception.

If you enjoy creating agents, perfecting training pipelines, and experimenting with new segmentation and scene understanding techniques, this role is your playground.

Key Responsibilities

1. Reinforcement Learning & Agents

   Develop and train reinforcement learning agents for robotic decision-making and scene understanding.
   Test policies in both simulation and real-world robotic platforms.

2. Computer Vision Foundations

   Build strong segmentation pipelines for weed/crop classification, object detection, and scene parsing.
   Apply and adapt classical and modern computer vision techniques (CNNs, transformers, feature extraction).

3. AI/ML Lifecycle

   Own the end-to-end pipeline: dataset preparation, training, testing, fine-tuning, and deployment.
   Continuously optimize models for efficiency and robustness on embedded systems.

4. Perception System Design

   Create agents for scene understanding and perception pipelines that integrate into ROS2.
   Explore multi-sensor fusion (camera, LiDAR, depth sensors) to strengthen perception accuracy.

5. LLMs + Robotics

   Experiment with large language models and explore their use in robotics (instruction following, semantic understanding, or pipeline integration).

6. Research to Implementation

   Don’t just read papers—prototype and implement novel algorithms, validate them in hardware, and push the boundaries of what’s possible.

Required Qualifications: 

1. Experience in reinforcement learning and agent-based methods.

2. Strong foundations in computer vision (segmentation, detection, feature matching, deep networks).

3. Proficiency with TensorFlow, PyTorch, CUDA, and debugging model pipelines.

4. Familiarity with ROS2 and deploying ML/DL models into robotic systems.

5. Exposure to LLMs and curiosity to combine them with robotics use cases.

6. Hands-on approach: willing to test algorithms in real hardware, not just simulation.

7. A mindset that values experimentation, collaboration, and learning by doing.

ARTPARK @ IISc :  Innovation factory for next-gen robotics & AI
ARTPARK is India's leading deep-tech venture builder and incubator focused on robotics, connected autonomous systems, and AI. Leveraging our unique facilities and ecosystems, we strive to provide meaningful support to very early-stage startups building deep-tech products based in research. We are a nonprofit organization created by Indian Institute of Science (IISc, Bengaluru) with support from the Department of Science & Technology (Government of India) and the Government of Karnataka.