ML Engineer - Simulation (Universal Robots, Bangalore - India)

Originally posted 4 November 2026 by the employer.

About the role

As an ML Engineer on the Simulation team, you will train, evaluate, and ship perception and 3D generation models powering simulation platforms for UR cobots and MiR mobile robots. You will build data, training, and evaluation pipelines to turn research into production-ready models for object detection, pose estimation, and image-to-3D reconstruction.

What you'll do

• Train, fine-tune, and evaluate deep learning models for object detection, instance segmentation, and pose estimation across industrial and warehouse environments.
• Develop models for 3D asset generation and image-to-3D reconstruction to produce simulation-ready meshes, textures, and materials.
• Prototype and productionise deep learning methods including diffusion models, transformers, NeRF, and Gaussian splatting.
• Build scalable, reproducible training pipelines across cloud and on-premises GPU clusters with distributed training, experiment tracking, and model versioning.
• Post-process generated 3D assets into formats such as USD, URDF, and SDF, ensuring valid collision geometry and physical properties.
• Optimise models for inference speed and memory footprint using quantisation, ONNX, and TensorRT, and integrate them into simulation workflows and ROS2-based pipelines.

What you'll need

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Electrical Engineering, Robotics, or a related technical field.
• 3+ years of professional experience training and deploying machine learning models, with a primary focus on computer vision.
• Strong programming proficiency in Python, with hands-on experience using PyTorch or JAX to build custom models, loss functions, data loaders, and training loops.
• Practical experience training and evaluating models for object detection, segmentation, pose estimation, or 3D reconstruction/generation.
• Solid understanding of CNNs, transformers, camera models, projective geometry, coordinate transforms, and evaluation metrics.
• Experience with dataset versioning, experiment tracking tools like Weights & Biases or MLflow, and development in Linux environments with GPUs and containers.

More semiconductor jobs: Teradyne jobs · India jobs